Program Schedule for Uncertainty 99

Tutorials: Sunday, January 3, 1999

Tutorial A: 8:30am - 10:30am
Susan Dumais, Microsoft Research
Information Access and Retrieval
Tutorial B: 11:00am - 12:00pm and 1:30pm - 2:30pm
David Spiegelhalter, MRC Biostatistics Unit, Institute for Public Health, Cambridge
Bayesian Statistical Analysis
Tutorial C: 3.30pm - 5:00pm
Trevor Hastie, Stanford University
Additive Logistic Regression: A Statistical View of Boosting
Banquet: 7:00pm
Speaker: Ed George

Monday Jan 4

7:30 to 8:45 REGISTRATION/CONTINENTAL BREAKFAST

8:45 to 9:00 OPENING COMMENTS
David Heckerman, Joe Whittaker

9:00 to 11:00 SESSION 1 Model Choice CHAIR: Thomas Richardson

Pedro Domingos	Process-oriented evaluation: The next step
Alan Gelfand, Sujit Ghosh	Model choice
Murlikrishna Viswanathan	A note on the comparison of polynomial selection methods
Matthew Brand	Pattern discovery via entropy minimization

11:00 to 11:30 BREAK

11:30 to 12:30 SESSION 2 Latent variables CHAIR: Kathyrn Laskey

Dan Geiger, David Heckerman, Henry King, Chris Meek	On the geometry of DAG models with hidden variables
Thomas Richardson, Heiko Bailer, Mooulinath Bannerjee	Efficient structure search in the presence of latent variables

12:30 to 1:30 LUNCH (provided)

1:30 to 5:00 BREAK

5:00 to 6:00 POSTER SUMMARIES (2 mins/poster) CHAIR: Joe Whittaker

6:00 to 7:00 DINNER

7:00 to 9:30 POSTER SESSIONS

Tuesday Jan 5

8:00 to 9:00 CONTINENTAL BREAKFAST

9:00 to 10:00 SESSION 3 Theory CHAIR: David Madigan

Phil Dawid, Milan Studeny	Conditional products: an alternative approach to conditional independence
Wenxin Jiang, Martin Tanner	Hierarchical mixtures-of-experts for generalized linear models:some results on denseness and consistency

10:00 to 10:30 COFFEE BREAK

10:30 to 11:30 SESSION 4 Regression CHAIR: Padhraic Smyth

Greg Ridgeway, David Madigan, Thomas Richardson	Boosting methodology for regression problems
Tommi Jaakkola, David Haussler	Probabilistic kernel regression models

11:30 to 12:30 SESSION 5 Computational Methods CHAIR: Padhraic Smyth

Nir Friedman, Lise Getoor	Learning structure from data efficiently: applying bounding techniques
Tim Oates, Paul Cohen, Casey Durfee	Efficient mining of statistical dependencies

12:30 to 2:00 LUNCH (provided)

2:00 to 3:30 SESSION 6 Applications CHAIR:

Louis A Cox	Causal mechanisms and classification trees for predicting chemical carcinogens
Jan De Geeter	Geometric modelling of a nuclear environment
Lewis Frey, Doug Fisher	Modeling decision tree performance with the power law

3:30 to 4:40 BUSINESS MEETING

Wednesday Jan 6

8:00 to 9:00 CONTINENTAL BREAKFAST

9:00 to 10:30 SESSION 7 Inference CHAIR: Greg Cooper

Michael Haft, Reimar Hofmann, Volker Tresp	Model-independent mean field theory as a local method for approximate propagation of information
H Attias	Hierarchical IFA belief networks
Kalev Kask, Rina Dechter	Stochastic local search for Bayesian network

10:30 to 11:00 COFFEE BREAK

11:00 to 12:00 SESSION 8 Applications CHAIR: Doug Fisher

Peter Spirtes, Greg Cooper	An experiment in causal discovery using a pneumona database
David Madigan	Bayesian graphical models for non-compliance in randomaized trials

12:00 to 12:15 CLOSING REMARKS

Plenary Presentations will last 25 minutes with 5 minutes for questions

Poster Sessions

Almond Herskovits Mislevey Steinberg	Transfer of information between system and evidence models
Chien George	Bayesian collaborative filtering
Cowell	Parameter learning from incomplete data for Bayesian networks
Friedman Goldszmidt Wyner	On the application of the bootstrap for computing confidence measures on features of induced Bayesian networks
Golinelli Madigan Consonni	Relaxing the local independence assumption for quantitative learning in acyclic directed graphical models through hierarchical partition models
Humphreys Titterington	A new method of learning in binary Boltzmann machines
Jensen	Statistical Challenges to inductive inference in linked data
Jorgensen Hunt	Mixture model clustering with the multimix program
Keogh Pazzani	Algorithms for learning augmented bayesian classifiers
Kontkanen Myllymaki Silander Tirri	Exploring the robustness of Bayesian and information-theoretic methods for predictive inference
Kreutz Reimetz Sendhoff Weihs Seelen	Structure optimization of density estimation models applied to regression problems with dynamic noise
Larkin	A learning rule based method of feature extraction with application to acoustic signal classification
Laskey	Learning extensible multi-entity directed graphical models
Monti Cooper	A latent variable model for multivariate discretization
Pearl Meshkat	Testing regression models with fewer regressors
Ramoni Sebastiani	Learning conditional probabilities from incomplete data: an experimental comparison
Rida Labbi Pelegrini	Experts combination through density decomposition
Roedder	Entropy driven probabilistic inference and inconsistency
Schmill Cohen	Learned models for continuous planning
Schubert	Efficient optimization of large k real-time control algorithm
Sebastiani Ramoni	Model folding for data subject to nonresponse
Settimi Smith	Geometry moments and Bayesian networks with hidden variables
Smyth	Joint probabilistic clustering of multivariate and sequential data
Stanghellini Whittaker	Analysis of multivariate time series via a hidden graphical model
Vogler	Visual design support for probabilistic network application