[edit]

Program Schedule

All times are GMT+7. You can check the current GMT+7 time here. Please check the Poster Assignments section to see which session your poster has been assigned to.

Schedule for Day 1: Saturday, May 3

Day 1: May 3 (Saturday)

08:30–09:00	Opening Remarks
09:00–10:00	Keynote Talk 1 by Chris Holmes
10:00–10:30	Coffee Break
10:30–11:30	Oral Session 1 | Deep Learning and Learning Theory Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much? Learning Graph Node Embeddings by Smooth Pair Sampling Loss Gradient Gaussian Width based Generalization and Optimization Guarantees
11:30–12:30	Panel
12:30–14:00	Lunch Break + DEI Events
14:00–15:00	Oral Session 2 | Distribution Learning and Causality Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation Additive Model Boosting: New Insights and Path(ologie)s Distributional Counterfactual Explanations With Optimal Transport Causal discovery in mixed additive noise models On Distributional Discrepancy for Experimental Design with General Assignment Probabilities
15:00–18:00	Poster Session 1
18:00 onward	Opening Reception

Schedule for Day 2: Sunday, May 4

Day 2: May 4 (Sunday)

09:00–10:00	Keynote Talk 2 by Aapo Hyvärinen
10:00–10:30	Coffee Break
10:30–11:30	Oral Session 3 | Optimization The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control Cubic regularized subspace Newton for non-convex optimization Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs Implicit Diffusion: Efficient optimization through stochastic sampling ScoreFusion: Fusing Score-based Generative Models via Kullback-Leibler Barycenters
11:30–12:30	Award Talks (ToT and best paper)
12:30–14:00	Lunch Break + DEI Events
14:00–15:00	Oral Session 4 | Privacy and Games Almost linear time differentially private release of synthetic graphs Balls-and-Bins Sampling for DP-SGD Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage A Novel Convex Gaussian Min Max Theorem for Repeated Features The Sample Complexity of Stackelberg Games
15:00–18:00	Poster Session 2

Schedule for Day 3: Monday, May 5

Day 3: May 5 (Monday)

09:00–10:00	Keynote Talk 3 by Akshay Krishnamurthy
10:00–10:30	Coffee Break
10:30–11:30	Oral Session 5 | Probabilistic Inference and Optimzation posteriordb: Testing, Benchmarking and Developing Bayesian Inference Algorithms Entropic Matching for Expectation Propagation of Markov Jump Processes Variation Due to Regularization Tractably Recovers Bayesian Deep Learning Uncertainty Restructuring Tractable Probabilistic Circuits Information Transfer Across Clinical Tasks via Adaptive Parameter Optimisation
11:30–12:30	Oral Session 6 | RL and Dynamical Systems Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data Corruption Robust Offline Reinforcement Learning with Human Feedback Pure Exploration with Feedback Graphs Near-Optimal Algorithm for Non-Stationary Kernelized Bandits Multi-marginal Schrodinger Bridges with Iterative Reference Refinement
12:30–14:00	Lunch Break + DEI Events
14:00–15:00	Oral Session 7 | Robust Learning Robust Kernel Hypothesis Testing under Data Corruption Learning from biased positive-unlabeled data via threshold calibration Statistical Learning of Distributionally Robust Stochastic Control in Continuous State Spaces A Robust Kernel Statistical Test of Invariance: Detecting Subtle Asymmetries Certifiably Quantisation-Robust training and inference of Neural Networks
15:00–18:00	Poster Session 3

Poster Assignments

Please click on each session to view the full list of posters included.

Poster Session 1

116 | Almost linear time differentially private release of synthetic graphs

355 | Hybrid Transfer Reinforcement Learning: Provable Sample Efficiency from Shifted-Dynamics Data

19 | Locally Private Estimation with Public Features

42 | Bayesian Off-Policy Evaluation and Learning for Large Action Spaces

221 | Locally Private Sampling with Public Data

662 | TempTest: Local Normalization Distortion and the Detection of Machine-generated Text

863 | Analyzing the Role of Permutation Invariance in Linear Mode Connectivity

1009 | Recurrent Neural Goodness-of-Fit Test for Time Series

1384 | Stochastic Approximation with Unbounded Markovian Noise: A General-Purpose Theorem

1492 | Fast Convergence of Softmax Policy Mirror Ascent

1512 | Bridging the Theoretical Gap in Randomized Smoothing

2062 | Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory

2126 | Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment

689 | The Sample Complexity of Stackelberg Games

89 | Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks

261 | Steering No-Regret Agents in MFGs under Model Uncertainty

337 | Planning and Learning in Risk-Aware Restless Multi-Arm Bandits

346 | Pareto Set Identification With Posterior Sampling

395 | Optimal Multi-Objective Best Arm Identification with Fixed Confidence

514 | Learning to Negotiate via Voluntary Commitment

529 | Transformers are Provably Optimal In-context Estimators for Wireless Communications

532 | Multi-Player Approaches for Dueling Bandits

537 | Provable Benefits of Task-Specific Prompts for In-context Learning

542 | Minimum Empirical Divergence for Sub-Gaussian Linear Bandits

796 | Fair Resource Allocation in Weakly Coupled Markov Decision Processes

843 | MDP Geometry, Normalization and Reward Balancing Solvers

911 | Is Prior-Free Black-Box Non-Stationary Reinforcement Learning Feasible?

923 | Learning Infinite-Horizon Average-Reward Linear Mixture MDPs of Bounded Span

954 | A Safe Bayesian Learning Algorithm for Constrained MDPs with Bounded Constraint Violation

993 | On Preference-based Stochastic Linear Contextual Bandits with Knapsacks

1198 | Independent Learning in Performative Markov Potential Games

1220 | Narrowing the Gap between Adversarial and Stochastic MDPs via Policy Optimization

1282 | A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration

1469 | Risk-sensitive Bandits: Arm Mixture Optimality and Regret-efficient Algorithms

1594 | Linear Submodular Maximization with Bandit Feedback

1610 | Time-varying Gaussian Process Bandits with Unknown Prior

1669 | Offline Multi-task Transfer RL with Representational Penalization

1687 | Bypassing the Exponential Dependency: Looped Transformers Efficiently Learn In-context by Multi-step Gradient Descent

1689 | Online Assortment and Price Optimization Under Contextual Choice Models

1761 | Federated Communication-Efficient Multi-Objective Optimization

1781 | Variational Adversarial Training Towards Policies with Improved Robustness

2042 | DPFL: Decentralized Personalized Federated Learning

385 | Distributional Counterfactual Explanations With Optimal Transport

309 | Microfoundation inference for strategic prediction

332 | Type Information-Assisted Self-Supervised Knowledge Graph Denoising

335 | Learning the Distribution Map in Reverse Causal Performative Prediction

336 | Optimizing Neural Network Training and Quantization with Rooted Logistic Objectives

402 | Evaluating Prediction-based Interventions with Human Decision Makers In Mind

504 | Differentially private algorithms for linear queries via stochastic convex optimization

555 | Training LLMs with MXFP4

703 | Towards Fair Graph Learning without Demographic Information

718 | A Causal Framework for Evaluating Deferring Systems

806 | FLIPHAT: Joint Differential Privacy for High Dimensional Linear Bandits

838 | Conditional Prediction ROC Bands for Graph Classification

1173 | Differential Privacy in Distributed Learning: Beyond Uniformly Bounded Stochastic Gradients

1606 | Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization

1937 | Knowledge Graph Completion with Mixed Geometry Tensor Factorization

741 | A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities

118 | A Bias-Variance Decomposition for Ensembles over Multiple Synthetic Datasets

177 | Fourier Circuits in Neural Networks and Transformers: A Case Study of Modular Arithmetic with Multiple Inputs

249 | A Generalized Theory of Mixup for Structure-Preserving Synthetic Data

303 | Fundamental Limits of Perfect Concept Erasure

426 | Learning a Single Index Model from Anisotropic Data with Vanilla Stochastic Gradient Descent

646 | QuACK: A Multipurpose Queuing Algorithm for Cooperative $k$-Armed Bandits

709 | Gaussian Smoothing in Saliency Maps: The Stability-Fidelity Trade-Off in Neural Network Interpretability

730 | Incremental Uncertainty-aware Performance Monitoring with Active Labeling Intervention

842 | Fundamental computational limits of weak learnability in high-dimensional multi-index models

851 | Time-series attribution maps with regularized contrastive learning

975 | A Tight Regret Analysis of Non-Parametric Repeated Contextual Brokerage

1041 | Sampling in High-Dimensions using Stochastic Interpolants and Forward-Backward Stochastic Differential Equations

1188 | Fixed-Budget Change Point Identification in Piecewise Constant Bandits

1348 | Towards Cost Sensitive Decision Making

1375 | On the Computational Tractability of the (Many) Shapley Values

1728 | Faster WIND: Accelerating Iterative Best-of-$N$ Distillation for LLM Alignment

1874 | How Well Can Transformers Emulate In-Context Newton's Method?

2065 | An Empirical Bernstein Inequality for Dependent Data in Hilbert Spaces and Applications

2122 | Emergence of Globally Attracting Fixed Points in Deep Neural Networks With Nonlinear Activations

845 | Variation Due to Regularization Tractably Recovers Bayesian Deep Learning Uncertainty

958 | Statistical Learning of Distributionally Robust Stochastic Control in Continuous State Spaces

1112 | Causal discovery in mixed additive noise models

47 | On the Convergence of Locally Adaptive and Scalable Diffusion-Based Sampling Methods for Deep Bayesian Neural Network Posteriors

50 | Fine-Tuning with Uncertainty-Aware Priors Makes Vision and Language Foundation Models More Reliable

102 | Bayesian Gaussian Process ODEs via Double Normalizing Flows

109 | Choice is what matters after Attention

168 | Function-Space MCMC for Bayesian Wide Neural Networks

266 | The Polynomial Iteration Complexity for Variance Exploding Diffusion Models: Elucidating SDE and ODE Samplers

503 | A Shared Low-Rank Adaptation Approach to Personalized RLHF

690 | Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections

733 | Legitimate ground-truth-free metrics for deep uncertainty classification scoring

740 | Common Learning Constraints Alter Interpretations of Direct Preference Optimization

914 | Your Finetuned Large Language Model is Already a Powerful Out-of-distribution Detector

1306 | Infinite-dimensional Diffusion Bridge Simulation via Operator Learning

1457 | Tighter Confidence Bounds for Sequential Kernel Regression

1559 | Deep Generative Quantile Bayes

1591 | Effective Bayesian Causal Inference via Structural Marginalisation and Autoregressive Orders

1996 | On Local Posterior Structure in Deep Ensembles

2021 | Level Set Teleportation: An Optimization Perspective

29 | Randomized Iterative Solver as Iterative Refinement: A Simple Fix Towards Backward Stability

88 | Estimation of Large Zipfian Distributions with Sort and Snap

138 | Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits

301 | Near-optimal algorithms for private estimation and sequential testing of collision probability

352 | HAR-former: Hybrid Transformer with an Adaptive Time-Frequency Representation Matrix for Long-Term Series Forecasting

378 | Prior-Fitted Networks Scale to Larger Datasets When Treated as Weak Learners

412 | Bandit Pareto Set Identification in a Multi-Output Linear Model

447 | Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model

469 | Optimal downsampling for Imbalanced Classification with Generalized Linear Models

487 | MEDUSA: Medical Data Under Shadow Attacks via Hybrid Model Inversion

536 | Improved dependence on coherence in eigenvector and eigenvalue estimation error bounds

622 | Approximating the Total Variation Distance between Gaussians

697 | Distribution-Aware Mean Estimation under User-level Local Differential Privacy

893 | Looped ReLU MLPs May Be All You Need as Practical Programmable Computers

1118 | Differentiable Causal Structure Learning with Identifiability by NOTIME

1121 | Out-of-distribution robustness for multivariate analysis via causal regularisation

1169 | Sketch-and-Project Meets Newton Method: Global O(1/k^2) Convergence with Low-Rank Updates

1235 | Online-to-PAC generalization bounds under graph-mixing dependencies

1506 | The Size of Teachers as a Measure of Data Complexity: PAC-Bayes Excess Risk Bounds and Scaling Laws

1547 | Bayesian Principles Improve Prompt Learning In Vision-Language Models

1569 | InfoNCE: Identifying the Gap Between Theory and Practice

1583 | Robust Estimation in metric spaces: Achieving Exponential Concentration with a Fr\'echet Median

1741 | General Staircase Mechanisms for Optimal Differential Privacy

1904 | Gaussian Mean Testing under Truncation

2007 | Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory

2059 | Hypernym Bias: Unraveling Deep Classifier Training Dynamics through the Lens of Class Hierarchy

143 | Near-Optimal Algorithm for Non-Stationary Kernelized Bandits

320 | Balls-and-Bins Sampling for DP-SGD

1548 | Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs

40 | Efficient Estimation of a Gaussian Mean with Local Differential Privacy

440 | Robust Score Matching

451 | Unbiased Quantization of the $L_1$ Ball for Communication-Efficient Distributed Mean Estimation

598 | Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference

667 | Differentially Private Continual Release of Histograms and Related Queries

681 | LMEraser: Large Model Unlearning via Adaptive Prompt Tuning

767 | Efficient Exploitation of Hierarchical Structure in Sparse Reward Reinforcement Learning

846 | Variance-Dependent Regret Bounds for Nonstationary Linear Bandits

1197 | Global Ground Metric Learning with Applications to scRNA data

1550 | Privacy in Metalearning and Multitask Learning: Modeling and Separations

1575 | Local Stochastic Sensitivity Analysis For Dynamical Systems

1601 | Signal Recovery from Random Dot-Product Graphs under Local Differential Privacy

1617 | Behavior-Inspired Neural Networks for Relational Inference

1807 | Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problem

1892 | Deep Clustering via Probabilistic Ratio-Cut Optimization

1984 | Counting Graphlets of Size k under Local Differential Privacy

401 | Symmetry-Based Structured Matrices for Efficient Approximately Equivariant Networks

101 | Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift

184 | Scalable spectral representations for multiagent reinforcement learning in network MDPs

187 | Bridging Domains with Approximately Shared Features

347 | Convergence Analysis for General Probability Flow ODEs of Diffusion Models in Wasserstein Distances

524 | An Adaptive Method for Weak Supervision with Drifting Data

769 | Distributional Adversarial Loss

852 | A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs

1194 | Sample Compression Unleashed: New Generalization Bounds for Real Valued Losses

1475 | Steinmetz Neural Networks for Complex-Valued Data

1520 | Theoretical Analysis of Leave-one-out Cross Validation for Non-differentiable Penalties under High-dimensional Settings

1685 | Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning

1756 | Optimal Stochastic Trace Estimation in Generative Modeling

1792 | Order-Optimal Regret in Distributed Kernel Bandits

1961 | Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions

2056 | AlleNoise - large-scale text classification benchmark dataset with real-world label noise

1275 | Variational Inference in Location-Scale Families: Exact Recovery of the Mean and Correlation Matrix

1446 | Multi-marginal Schrödinger Bridges with Iterative Reference Refinement

11 | Cost-aware simulation-based inference

174 | On the Asymptotic Mean Square Error Optimality of Diffusion Models

190 | Epistemic Uncertainty and Excess Risk in Variational Inference

259 | Amortized Probabilistic Conditioning for Optimization, Simulation and Inference

494 | Proximal Sampler with Adaptive Step Size

506 | Recursive Learning of Asymptotic Variational Objectives

594 | Adaptive RKHS Fourier Features for Compositional Gaussian Process Models

677 | Information-Theoretic Causal Discovery in Topological Order

734 | Information-Theoretic Measures on Lattices for Higher-Order Interactions

756 | ChronosX: Adapting Pretrained Time Series Models with Exogenous Variables

892 | A Multi-Task Learning Approach to Linear Multivariate Forecasting

1049 | Functional Stochastic Gradient MCMC for Bayesian Neural Networks

1126 | Memorization in Attention-only Transformers

1498 | Application of Structured State Space Models to High energy physics with locality sensitive hashing

1519 | SteinDreamer: Variance Reduction for Text-to-3D Score Distillation via Stein Identity

1554 | All or None: Identifiable Linear Properties of Next-Token Predictors in Language Modeling

1598 | Cross-modality Matching and Prediction of Perturbation Responses with Labeled Gromov-Wasserstein Optimal Transport

1632 | Cross-Modal Imputation and Uncertainty Estimation for Spatial Transcriptomics

1716 | Batch, match, and patch: low-rank approximations for score-based variational inference

1891 | Learning Stochastic Nonlinear Dynamics with Embedded Latent Transfer Operators

541 | Importance-weighted Positive-unlabeled Learning for Distribution Shift Adaptation

620 | Learning Graph Node Embeddings by Smooth Pair Sampling

9 | Automatically Adaptive Conformal Risk Control

98 | Conditional Generative Learning from Invariant Representations in Multi-Source: Robustness and Efficiency

179 | Signature Isolation Forest

230 | Reinforcement Learning for Adaptive MCMC

384 | Model selection for behavioral learning data and applications to contextual bandits

465 | SubSearch: Robust Estimation and Outlier Detection for Stochastic Block Models via Subgraph Search

564 | Reinforcement Learning with Intrinsically Motivated Feedback Graph for Lost-sales Inventory Control

596 | Statistical Inference for Feature Selection after Optimal Transport-based Domain Adaptation

635 | Hierarchical Bias-Driven Stratification for Interpretable Causal Effect Estimation

651 | Changepoint Estimation in Sparse Dynamic Stochastic Block Models under Near-Optimal Signal Strength

917 | Spectral Representation for Causal Estimation with Hidden Confounders

982 | Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons

1109 | HACSurv: A Hierarchical Copula-Based Approach for Survival Analysis with Dependent Competing Risks

Poster Session 2

1225 | SNAP: Sequential Non-Ancestor Pruning for Targeted Causal Effect Estimation With an Unknown Graph

1355 | Survival Models: Proper Scoring Rule and Stochastic Optimization with Competing Risks

1407 | Scalable Out-of-Distribution Robustness in the Presence of Unobserved Confounders

1472 | Max-Rank: Efficient Multiple Testing for Conformal Prediction

1567 | Double Debiased Machine Learning for Mediation Analysis with Continuous Treatments

1734 | Causal Temporal Regime Structure Learning

2046 | Density Ratio-based Proxy Causal Learning Without Density Ratios

423 | posteriordb: Testing, Benchmarking and Developing Bayesian Inference Algorithms

670 | Implicit Diffusion: Efficient optimization through stochastic sampling

1627 | Loss Gradient Gaussian Width based Generalization and Optimization Guarantees

125 | Generalization Lower Bounds for GD and SGD in Smooth Stochastic Convex Optimization

150 | Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization

276 | Ordered $\mathcal{V}$-information Growth: A Fresh Perspective on Shared Information

394 | Variational Inference on the Boolean Hypercube with the Quantum Entropy

584 | Cross Validation for Correlated Data in Classification Models

590 | Truncated Inverse-Lévy Measure Representation of the Beta Process

826 | Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration

899 | Q-learning for Quantile MDPs: A Decomposition, Performance, and Convergence Analysis

979 | Evidential Uncertainty Probes for Graph Neural Networks

1136 | Infinite Width Limits of Self Supervised Neural Networks

1412 | SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching

1497 | Scalable Implicit Graphon Learning

1524 | Sampling from the Random Linear Model via Stochastic Localization Up to the AMP Threshold

1957 | Robust Classification by Coupling Data Mollification with Label Smoothing

31 | Flexible Copula-Based Mixed Models in Deep Learning: A Scalable Approach to Arbitrary Marginals

120 | Approximate information maximization for bandit games

162 | Ant Colony Sampling with GFlowNets for Combinatorial Optimization

446 | Parameter estimation in state space models using particle importance sampling

608 | Hyperboloid GPLVM for Discovering Continuous Hierarchies via Nonparametric Estimation

726 | Classification of High-dimensional Time Series in Spectral Domain Using Explainable Features with Applications to Neuroimaging Data

837 | Zero-Shot Action Generalization with Limited Observations

927 | Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields

960 | Calm Composite Losses: Being Improper Yet Proper Composite

1025 | New User Event Prediction Through the Lens of Causal Inference

1053 | Meta-learning from Heterogeneous Tensors for Few-shot Tensor Completion

1216 | A Differential Inclusion Approach for Learning Heterogeneous Sparsity in Neuroimaging Analysis

1618 | MODL: Multilearner Online Deep Learning

1649 | Posterior Mean Matching: Generative Modeling through Online Bayesian Inference

1774 | Learning to Forget: Bayesian Time Series Forecasting using Recurrent Sparse Spectrum Signature Gaussian Processes

17 | Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel–Young Loss Perspective and Gap-Dependent Regret Analysis

41 | Credal Two-Sample Tests of Epistemic Uncertainty

204 | Empirical Error Estimates for Graph Sparsification

295 | Tamed Langevin sampling under weaker conditions

519 | Fully Dynamic Adversarially Robust Correlation Clustering in Polylogarithmic Update Time

640 | RetroDiff: Retrosynthesis as Multi-stage Distribution Interpolation

657 | Contractivity and linear convergence in bilinear saddle-point problems: An operator-theoretic approach

857 | Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis

915 | When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?

983 | Memory-Efficient Optimization with Factorized Hamiltonian Descent

985 | Computing high-dimensional optimal transport by flow neural networks

996 | Decoupling epistemic and aleatoric uncertainties with possibility theory

1060 | Domain Adaptation and Entanglement: an Optimal Transport Perspective

1274 | Optimal Time Complexity Algorithms for Computing General Random Walk Graph Kernels on Sparse Graphs

1361 | Offline RL via Feature-Occupancy Gradient Ascent

1373 | Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory

1471 | Learning Geometrically-Informed Lyapunov Functions with Deep Diffeomorphic RBF Networks

1513 | Distributional Off-policy Evaluation with Bellman Residual Minimization

1871 | Structure based SAT dataset for analysing GNN generalisation

1909 | Mixed-Feature Logistic Regression Robust to Distribution Shifts

1626 | ScoreFusion: Fusing Score-based Generative Models via Kullback–Leibler Barycenters

78 | A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning

300 | Poisoning Bayesian Inference via Data Deletion and Replication

305 | Perfect Recovery for Random Geometric Graph Matching with Shallow Graph Neural Networks

315 | Heterogeneous Graph Structure Learning through the Lens of Data-generating Processes

331 | Distance Estimation for High-Dimensional Discrete Distributions

379 | Locally Optimal Descent for Dynamic Stepsize Scheduling

428 | A primer on linear classification with missing data

444 | On the Relationship Between Robustness and Expressivity of Graph Neural Networks

482 | Integer Programming Based Methods and Heuristics for Causal Graph Learning

603 | On Tractability of Learning Bayesian Networks with Ancestral Constraints

637 | Model Evaluation in the Dark: Robust Classifier Metrics with Missing Labels

777 | Credibility-Aware Multimodal Fusion Using Probabilistic Circuits

812 | When the Universe is Too Big: Bounding Consideration Probabilities for Plackett-Luce Rankings

834 | Deep Optimal Sensor Placement for Black Box Stochastic Simulations

1028 | Variational Combinatorial Sequential Monte Carlo for Bayesian Phylogenetics in Hyperbolic Space

1292 | Fairness Risks for Group-Conditionally Missing Demographics

1336 | Rethinking Neural-based Matrix Inversion: Why can't, and Where can

1370 | Theoretically Grounded Pruning of Large Ground Sets for Constrained, Discrete Optimization

1448 | RTD-Lite: Scalable Topological Analysis for Comparing Weighted Graphs in Learning Tasks

1700 | SINE: Scalable MPE Inference for Probabilistic Graphical Models using Advanced Neural Embeddings

1743 | Understanding the Effect of GCN Convolutions in Regression Tasks

1798 | $\mathcal{I}$-trustworthy Models. A framework for trustworthiness evaluation of probabilistic classifiers

1939 | Unconditionally Calibrated Priors for Beta Mixture Density Networks

123 | Disentangling impact of capacity, objective, batchsize, estimators, and step-size on flow VI

176 | Adaptive Extragradient Methods for Root-finding Problems under Relaxed Assumptions

485 | The VampPrior Mixture Model

949 | Causal Discovery on Dependent Binary Data

987 | Is Gibbs sampling faster than Hamiltonian Monte Carlo on GLMs?

1114 | Riemann$^2$: Learning Riemannian Submanifolds from Riemannian Data

1133 | Continuous Structure Constraint Integration for Robust Causal Discovery

1165 | TRADE: Transfer of Distributions between External Conditions with Normalizing Flows

1256 | Separation-Based Distance Measures for Causal Graphs

1264 | Enhanced Adaptive Gradient Algorithms for Nonconvex-PL Minimax Optimization

1388 | Learning Visual-Semantic Subspace Representations

1452 | Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees

1462 | InnerThoughts: Disentangling Representations and Predictions in Large Language Models

1605 | Synthetic Potential Outcomes and Causal Mixture Identifiability

1722 | Beyond Discretization: Learning the Optimal Solution Path

1828 | Graph-based Complexity for Causal Effect by Empirical Plug-in

1989 | Sampling from Bayesian Neural Network Posteriors with Symmetric Minibatch Splitting Langevin Dynamics

2089 | Training Neural Samplers with Reverse Diffusive KL Divergence

2097 | Mean-Field Microcanonical Gradient Descent

885 | Robust Kernel Hypothesis Testing under Data Corruption

21 | A Family of Distributions of Random Subsets for Controlling Positive and Negative Dependence

35 | Bayesian Inference in Recurrent Explicit Duration Switching Linear Dynamical Systems

128 | Strong Screening Rules for Group-based SLOPE Models

149 | Nonparametric Factor Analysis and Beyond

151 | Scalable Inference for Bayesian Multinomial Logistic-Normal Dynamic Linear Models

475 | UNHaP: Unmixing Noise from Hawkes Processes

696 | Robust Gradient Descent for Phase Retrieval

1262 | FreqMoE: Enhancing Time Series Forecasting through Frequency Decomposition Mixture of Experts

1283 | A graphical global optimization framework for parameter estimation of statistical models with nonconvex regularization functions

1288 | High-Dimensional Differential Parameter Inference in Exponential Family using Time Score Matching

1290 | Large Covariance Matrix Estimation With Nonnegative Correlations

1319 | Nonparametric estimation of Hawkes processes with RKHSs

1764 | Understanding the Learning Dynamics of LoRA: A Gradient Flow Perspective on Low-Rank Adaptation in Matrix Factorization

2001 | Personalizing Low-Rank Bayesian Neural Networks Via Federated Learning

1149 | What Ails Generative Structure-based Drug Design: Expressivity is Too Little or Too Much?

159 | HAVER: Instance-Dependent Error Bounds for Maximum Mean Estimation and Applications to Q-Learning and Monte Carlo Tree Search

171 | Signed Graph Autoencoder for Explainable and Polarization-Aware Network Embeddings

270 | Stein Boltzmann Sampling: A Variational Approach for Global Optimization

458 | MING: A Functional Approach to Learning Molecular Generative Models

499 | Rate of Model Collapse in Recursive Training

568 | AxlePro: Momentum-Accelerated Batched Training of Kernel Machines

591 | Consistent Amortized Clustering via Generative Flow Networks

653 | Multi-Agent Credit Assignment with Pretrained Language Models

702 | Calibrated Computation-Aware Gaussian Processes

719 | Generalization Bounds for Dependent Data using Online-to-Batch Conversion.

784 | Near-Polynomially Competitive Active Logistic Regression

880 | Improving N-Glycosylation and Biopharmaceutical Production Predictions Using AutoML-Built Residual Hybrid Models

883 | Parabolic Continual Learning

1013 | Transfer Learning for High-dimensional Reduced Rank Time Series Models

1085 | Meta-learning Task-specific Regularization Weights for Few-shot Linear Regression

1247 | Vecchia Gaussian Process Ensembles on Internal Representations of Deep Neural Networks

1363 | Gated Recurrent Neural Networks with Weighted Time-Delay Feedback

1383 | Conditioning diffusion models by explicit forward-backward bridging

1460 | Adapting to Online Distribution Shifts in Deep Learning: A Black-Box Approach

1767 | Variational Schr\"odinger Momentum Diffusion

1823 | Regularity in Canonicalized Models: A Theoretical Perspective

1981 | LITE: Efficiently Estimating Gaussian Probability of Maximality

2034 | On the Convergence of Continual Federated Learning Using Incrementally Aggregated Gradients

2040 | Analyzing Generative Models by Manifold Entropic Metrics

16 | Generalized Criterion for Identifiability of Additive Noise Models Using Majorization

68 | S-CFE: Simple Counterfactual Explanations

127 | Learning in Herding Mean Field Games: Single-Loop Algorithm with Finite-Time Convergence Analysis

193 | Learning Identifiable Structures Helps Avoid Bias in DNN-based Supervised Causal Learning

262 | Bridging Multiple Worlds: Multi-marginal Optimal Transport for Causal Partial-identification Problem

268 | Optimal estimation of linear non-Gaussian structure equation models

479 | Axiomatic Explainer Globalness via Optimal Transport

616 | Factor Analysis with Correlated Topic Model for Multi-Modal Data

628 | Partial Information Decomposition for Data Interpretability and Feature Selection

680 | A Unified Evaluation Framework for Epistemic Predictions

685 | All models are wrong, some are useful: Model Selection with Limited Labels

717 | Disentangling Interactions and Dependencies in Feature Attributions

844 | BudgetIV: Optimal Partial Identification of Causal Effects with Mostly Invalid Instruments

965 | Optimistic Safety for Online Convex Optimization with Unknown Linear Constraints

1130 | Multimodal Learning with Uncertainty Quantification based on Discounted Belief Fusion

1145 | Safety in the Face of Adversity: Achieving Zero Constraint Violation in Online Learning with Slowly Changing Constraints

1172 | Statistical Test for Auto Feature Engineering by Selective Inference

1176 | On the Identifiability of Causal Abstractions

1193 | Tensor Network Based Feature Learning Model

1392 | Kernel Single Proxy Control for Deterministic Confounding

1401 | Copula Based Trainable Calibration Error Estimator of Multi-Label Classification with Label Interdependencies

1440 | On Subjective Uncertainty Quantification and Calibration in Natural Language Generation

1499 | Analysis of Two-Stage Rollout Designs with Clustering for Causal Inference under Network Interference

2100 | Clustering Context in Off-Policy Evaluation

2138 | The Strong Product Model for Network Inference without Independence Assumptions

142 | Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage

205 | On the Geometry and Optimization of Polynomial Convolutional Networks

206 | Data Reconstruction Attacks and Defenses: A Systematic Evaluation

244 | FedBaF: Federated Learning Aggregation Biased by a Foundation Model

363 | Learning-Augmented Algorithms for Online Concave Packing and Convex Covering Problems

510 | Improving Stochastic Cubic Newton with Momentum

525 | On the Inherent Privacy of Zeroth-Order Projected Gradient Descent

621 | Personalized Convolutional Dictionary Learning of Physiological Time Series

630 | Energy-consistent Neural Operators for Hamiltonian and Dissipative Partial Differential Equations

631 | On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark

686 | Active Bipartite Ranking with Smooth Posterior Distributions

832 | From Gradient Clipping to Normalization for Heavy Tailed SGD

835 | Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits

850 | Spectral Differential Network Analysis for High-Dimensional Time Series

859 | An Iterative Algorithm for Rescaled Hyperbolic Functions Regression

872 | Asynchronous Decentralized Optimization with Constraints: Achievable Speeds of Convergence for Directed Graphs

973 | Approximate Global Convergence of Independent Learning in Multi-Agent Systems

1057 | ADEPT: Hierarchical Bayes Approach to Personalized Federated Unsupervised Learning

1238 | Covariance Selection over Networks

1552 | Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent

1577 | Learning Gaussian Multi-Index Models with Gradient Flow: Time Complexity and Directional Convergence

1745 | Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints

1993 | Refined Analysis of Constant Step Size Federated Averaging and Federated Richardson-Romberg Extrapolation

2093 | Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants

2143 | A Convex Relaxation Approach to Generalization Analysis for Parallel Positively Homogeneous Networks

Poster Session 3

897 | Pick-to-Learn and Self-Certified Gaussian Process Approximations

106 | Density Ratio Estimation via Sampling along Generalized Geodesics on Statistical Manifolds

135 | Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation

144 | No-Regret Bayesian Optimization with Stochastic Observation Failures

198 | Selecting the Number of Communities for Weighted Degree-Corrected Stochastic Block Models

267 | To Give or Not to Give? The Impacts of Strategically Withheld Recourse

354 | Bayesian Decision Theory on Decision Trees: Uncertainty Evaluation and Interpretability

523 | Differentially Private Range Queries with Correlated Input Perturbation

557 | Multi-agent Multi-armed Bandit Regret Complexity and Optimality

582 | Bayesian Circular Regression with von Mises Quasi-Processes

691 | Computation-Aware Kalman Filtering and Smoothing

907 | Robust Multi-fidelity Bayesian Optimization with Deep Kernel and Partition

1014 | Decision-Point Guided Safe Policy Improvement

1132 | Koopman-Equivariant Gaussian Processes

1230 | Hyperbolic Prototypical Entailment Cones for Image Classification

1337 | A Safe Exploration Approach to Constrained Markov Decision Processes

1433 | Your copula is a classifier in disguise: classification-based copula density estimation

1474 | Near-Optimal Sample Complexity for Iterated CVaR Reinforcement Learning with a Generative Model

1528 | $q\texttt{POTS}$: Efficient Batch Multiobjective Bayesian Optimization via Pareto Optimal Thompson Sampling

1543 | Enhancing Feature-Specific Data Protection via Bayesian Coordinate Differential Privacy

1570 | Achieving $\widetilde{\mathcal{O}}(\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models

1588 | From Deep Additive Kernel Learning to Last-Layer Bayesian Neural Networks via Induced Prior Approximation

1713 | Cost-Aware Optimal Pairwise Pure Exploration

1715 | Understanding Expert Structures on Minimax Parameter Estimation in Contaminated Mixture of Experts

1760 | Differentially Private Kernelized Contextual Bandits

779 | Learning from biased positive-unlabeled data via threshold calibration

22 | Lower Bounds for Time-Varying Kernelized Bandits

129 | Infinite-Horizon Reinforcement Learning with Multinomial Logit Function Approximation

170 | A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning

292 | Collaborative non-parametric two-sample testing

374 | On the Power of Adaptive Weighted Aggregation in Heterogeneous Federated Learning and Beyond

473 | Noisy Low-Rank Matrix Completion via Transformed $L_1$ Regularization and its Theoretical Properties

658 | Change Point Detection in Hadamard Spaces by Alternating Minimization

795 | DeCaf: A Causal Decoupling Framework for OOD Generalization on Node Classification

877 | Sampling From Multiscale Densities With Delayed Rejection Generalized Hamiltonian Monte Carlo

935 | Learning Laplacian Positional Encodings for Heterophilous Graphs

939 | Understanding GNNs and Homophily in Dynamic Node Classification

1001 | Permutation Invariant Functions: Statistical Testing, Density Estimation, and Metric Entropy

1088 | Subspace Recovery in Winsorized PCA: Insights into Accuracy and Robustness

1186 | Composition and Control with Distilled Energy Diffusion Models and Sequential Monte Carlo

1301 | Diffusion Models under Group Transformations

1358 | Density-Dependent Group Testing

1404 | Causal Discovery-Driven Change Point Detection in Time Series

1470 | Semiparametric conformal prediction

1571 | Approximate Equivariance in Reinforcement Learning

1790 | Testing Conditional Independence with Deep Neural Network Based Binary Expansion Testing (DeepBET)

1800 | Quantile Additive Trend Filtering

1881 | Nonparametric Distributional Regression via Quantile Regression

1906 | Conformal Prediction Under Generalized Covariate Shift with Posterior Drift

296 | Entropic Matching for Expectation Propagation of Markov Jump Processes

104 | The Local Learning Coefficient: A Singularity-Aware Complexity Measure

318 | Superiority of Multi-Head Attention: A Theoretical Study in Shallow Transformers in In-Context Linear Regression

391 | $f$-PO: Generalizing Preference Optimization with $f$-divergence Minimization

505 | Is Merging Worth It? Securely Evaluating the Information Gain for Causal Dataset Acquisition

549 | Dissecting the Impact of Model Misspecification in Data-Driven Optimization

615 | From Learning to Optimize to Learning Optimization Algorithms

664 | StableMDS: A Novel Gradient Descent-Based Method for Stabilizing and Accelerating Weighted Multidimensional Scaling

774 | Global Optimization of Gaussian Process Acquisition Functions Using a Piecewise-Linear Kernel Approximation

822 | On adaptivity and minimax optimality of two-sided nearest neighbors

878 | Differentially Private Graph Data Release: Inefficiencies & Unfairness

921 | Geometric Collaborative Filtering with Convergence

974 | Protein Fitness Landscape: Spectral Graph Theory Perspective

1300 | Anytime-Valid A/B Testing of Counting Processes

1701 | Quantifying Knowledge Distillation using Partial Information Decomposition

1757 | Beyond Size-Based Metrics: Measuring Task-Specific Complexity in Symbolic Regression

1950 | Weighted Euclidean Distance Matrices over Mixed Continuous and Categorical Inputs for Gaussian Process Models

141 | Nyström Kernel Stein Discrepancy

273 | Score matching for bridges without learning time-reversals

290 | Consistent Validation for Predictive Methods in Spatial Settings

460 | Sequential Kernelized Stein Discrepancy

516 | Differentiable Calibration of Inexact Stochastic Simulation Models via Kernel Score Minimization

813 | Conditional diffusions for amortized neural posterior estimation

1302 | Theoretical Convergence Guarantees for Variational Autoencoders

1351 | Weighted Sum of Gaussian Process Latent Variable Models

1557 | Learning High-dimensional Gaussians from Censored Data

1709 | Efficient and Asymptotically Unbiased Constrained Decoding for Large Language Models

1721 | Stochastic Weight Sharing for Bayesian Neural Networks

1979 | Noise-Aware Differentially Private Variational Inference

1 | Additive Model Boosting: New Insights and Path(ologie)s

1676 | Corruption Robust Offline Reinforcement Learning with Human Feedback

95 | $\beta$-th order Acyclicity Derivatives for DAG Learning

381 | Policy Teaching via Data Poisoning in Learning from Human Preferences

551 | ROTI-GCV: Generalized Cross-Validation for right-ROTationally Invariant Data

558 | Models That Are Interpretable But Not Transparent

836 | Explaining ViTs Using Information Flow

1055 | HR-Bandit: Human-AI Collaborated Linear Recourse Bandit

1228 | Do Regularization Methods for Shortcut Mitigation Work As Intended?

1307 | Natural Language Counterfactual Explanations for Graphs Using Large Language Models

1581 | Variance-Aware Linear UCB with Deep Representation for Neural Contextual Bandits

1779 | Adversarial Vulnerabilities in Large Language Models for Time Series Forecasting

1907 | Robust Offline Policy Learning with Observational Data from Multiple Sources

1978 | Wasserstein Distributionally Robust Bayesian Optimization with Continuous Context

520 | On Distributional Discrepancy for Experimental Design with General Assignment Probabilities

4 | Paths and Ambient Spaces in Neural Loss Landscapes

39 | ClusterSC: Advancing Synthetic Control with Donor Selection

117 | Adversarial Training in High-Dimensional Regression: Generated Data and Neural Networks

236 | Harnessing Causality in Reinforcement Learning with Bagged Decision Times

425 | Efficient Optimization Algorithms for Linear Adversarial Training

474 | Representer Theorems for Metric and Preference Learning: Geometric Insights and Algorithms

553 | Towards a mathematical theory for consistency training in diffusion models

569 | A Likelihood Based Approach for Watermark Detection

901 | Sparse Activations as Conformal Predictors

1042 | Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs via Approximation by Discounted-Reward MDPs

1066 | Invertible Fourier Neural Operators for Tackling Both Forward and Inverse Problems

1115 | High Dimensional Bayesian Optimization using Lasso Variable Selection

1174 | Performative Reinforcement Learning with Linear Markov Decision Process

1180 | Powerful batch conformal prediction for classification

1260 | Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs

1366 | LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits

1444 | Primal-Dual Spectral Representation for Off-policy Evaluation

1814 | A Shapley-value Guided Rationale Editor for Rationale Learning

112 | The Pivoting Framework: Frank-Wolfe Algorithms with Active Set Size Control

288 | Cubic regularized subspace Newton for non-convex optimization

114 | Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties

152 | Inverse Optimization with Prediction Market: A Characterization of Scoring Rules for Elciting System States

513 | Adaptive Convergence Rates for Log-Concave Maximum Likelihood

623 | Performative Prediction on Games and Mechanism Design

873 | Synthesis and Analysis of Data as Probability Measures With Entropy-Regularized Optimal Transport

1106 | Stochastic Gradient Descent for Bézier Simplex Representation of Pareto Set in Multi-Objective Optimization

1204 | Parallel Backpropagation for Inverse of a Convolution with Application to Normalizing Flows

1417 | Two-Timescale Linear Stochastic Approximation: Constant Stepsizes Go a Long Way

1551 | Visualizing token importance for black-box language models

1636 | Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models

1647 | Stochastic Rounding for LLM Training: Theory and Practice

1737 | Linearized Wasserstein Barycenters: Synthesis, Analysis, Representational Capacity, and Applications

1820 | Bilevel Reinforcement Learning via the Development of Hyper-gradient without Lower-Level Convexity

1833 | Conditional simulation via entropic optimal transport: Toward non-parametric estimation of conditional Brenier maps

2064 | M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling

63 | Optimising Clinical Federated Learning through Mode Connectivity-based Model Aggregation

243 | Learning the Pareto Front Using Bootstrapped Observation Samples

297 | Global Group Fairness in Federated Learning via Function Tracking

298 | Near-Optimal Sample Complexity in Reward-Free Kernel-based Reinforcement Learning

351 | Q-function Decomposition with Intervention Semantics for Factored Action Spaces

361 | Trustworthy assessment of heterogeneous treatment effect estimator via analysis of relative error

619 | The Hardness of Validating Observational Studies with Experimental Data

708 | Data-Driven Upper Confidence Bounds with Near-Optimal Regret for Heavy-Tailed Bandits

761 | Efficient Trajectory Inference in Wasserstein Space Using Consecutive Averaging

1017 | Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality

1270 | Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis

1379 | Causal Representation Learning from General Environments under Nonparametric Mixing

1482 | Feasible Learning

1518 | Theory of Agreement-on-the-Line in Linear Models and Gaussian Data

1613 | Logarithmic Neyman Regret for Adaptive Estimation of the Average Treatment Effect

1621 | Active Feature Acquisition for Personalised Treatment Assignment

1631 | Graph Machine Learning based Doubly Robust Estimator for Network Causal Effects

1793 | On the Consistent Recovery of Joint Distributions from Conditionals

617 | Pure Exploration with Feedback Graphs

869 | Restructuring Tractable Probabilistic Circuits

183 | Elastic Representation: Mitigating Spurious Correlations for Group Robustness

251 | On the Sample Complexity of Next-Token Prediction

281 | On Tradeoffs in Learning-Augmented Algorithms

472 | Federated UCBVI: Communication-Efficient Federated Regret Minimization with Heterogeneous Agents

522 | Dynamic DBSCAN with Euler Tour Sequences

540 | Neural Point Processes for Pixel-wise Regression

574 | What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization

586 | Post-processing for Fair Regression via Explainable SVD

627 | A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models

722 | Accuracy on the wrong line: On the pitfalls of noisy data for out-of-distribution generalisation

749 | Best-Arm Identification in Unimodal Bandits

758 | Reward Maximization for Pure Exploration: Minimax Optimal Good Arm Identification for Nonparametric Multi-Armed Bandits

772 | A Subquadratic Time Approximation Algorithm for Individually Fair k-Center

799 | Robust Fair Clustering with Group Membership Uncertainty Sets

827 | Statistical Guarantees for Unpaired Image-to-Image Cross-Domain Analysis using GANs

1630 | On the Power of Multitask Representation Learning with Gradient Descent

1634 | M$^2$AD: Multi-Sensor Multi-System Anomaly Detection through Global Scoring and Calibrated Thresholding

1796 | Transfer Neyman-Pearson Algorithm for Outlier Detection

2057 | Strategic Conformal Prediction

2113 | Task-Driven Discrete Representation Learning

1234 | Information Transfer Across Clinical Tasks via Adaptive Parameter Optimisation

1372 | A Novel Convex Gaussian Min Max Theorem for Repeated Features

1838 | A Robust Kernel Statistical Test of Invariance: Detecting Subtle Asymmetries

2050 | Certifiably Quantisation-Robust training and inference of Neural Networks

224 | Reliable and Scalable Variable Importance Estimation via Warm-start and Early Stopping

231 | Prediction-Centric Uncertainty Quantification via MMD

271 | Learning signals defined on graphs with optimal transport and Gaussian process regression

275 | Safe exploration in reproducing kernel Hilbert spaces

291 | Get rid of your constraints and reparametrize: A study in NNLS and implicit bias

350 | Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds

380 | Online Student-$t$ Processes with an Overall-local Scale Structure for Modelling Non-stationary Data

552 | Clustered Invariant Risk Minimization

607 | High-probability Convergence Bounds for Online Nonlinear Stochastic Gradient Descent under Heavy-tailed Noise

721 | Tensor Network-Constrained Kernel Machines as Gaussian Processes

1040 | Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning

1239 | Sparse Causal Effect Estimation using Two-Sample Summary Statistics in the Presence of Unmeasured Confounding

1291 | TVineSynth: A Truncated C-Vine Copula Generator of Synthetic Tabular Data to Balance Privacy and Utility

1489 | Task Shift: From Classification to Regression in Overparameterized Linear Models

1507 | DDEQs: Distributional Deep Equilibrium Models through Wasserstein Gradient Flows

1535 | Estimating the Spectral Moments of the Kernel Integral Operator from Finite Sample Matrices

1573 | The cost of local and global fairness in Federated Learning

1746 | Learning Pareto manifolds in high dimensions: How can regularization help?

1777 | The Uniformly Rotated Mondrian Kernel

1803 | A Computation-Efficient Method of Measuring Dataset Quality based on the Coverage of the Dataset

1809 | Advancing Fairness in Precision Medicine: A Universal Framework for Optimal Treatment Estimation in Censored Data

1847 | Leveraging Frozen Batch Normalization for Co-Training in Source-Free Domain Adaptation

1913 | Algorithmic Accountability in Small Data: Sample-Size-Induced Bias Within Classification Metrics

1945 | Black-Box Uniform Stability for Non-Euclidean Empirical Risk Minimization