Program for AISTATS 2001

  • Thursday January 4: tutorials

    10.00 -- 12.00
    David Edwards (Novo Pharmaceutical Company)
    "Graphical models for mixed data : an introduction to the theory and practice"

    2.00 -- 4.00
    Yoav Freund (AT&T Research)
    "Predicting More -- Assuming Less, new methodologies in statistical inference"

    Coffee Break

    4.30 -- 6.30
    David MacKay (University of Cambridge)
    "Error correcting codes and belief propagation"

  • Friday January 5

    7.30 -- 8.45 Breakfast

    8.45 -- 9.00 Opening

    Morning 1: Clustering

    9.00 -- 9.30
    The Learning Curve Method Applied to Clustering
    Chris Meek, Bo Thiesson, David Heckerman

    9.30 -- 10.00
    Bootstrapping Self-Organizing Maps to Assess the Statistical Significance of Local Proximity
    Eric de Bodt, Marie Cottrell

    10.00 -- 10.30
    A Random Walks View of Spectral Segmentation
    Marina Meila, Jianbo Shi

    Coffee break

    Morning 2: Speech/language

    11.00 -- 11.30
    Distributional Similarity, Frequency, and the Skew Divergence
    Lillian Lee

    11.30 -- 12.00
    Handling Missing and Unreliable Information in Speech Recognition
    Phil Green, Martin Cooke, Jon Barker, Ljubomir Josifovski

    12.00 -- 2.00 Conference lunch

    Afternoon: Graphical Model search

    2.00 -- 2.30
    Finding an optimal chain is harder than finding an optimal tree
    Chris Meek

    2.30 -- 3.00
    An Anytime Algorithm for Causal Inference
    Peter Spirtes

    3.00 -- 3.30
    A Simulation Study of Three Related Causal Data Mining Algorithms
    Subramani Mani, Gregory Cooper

    Coffee break

    4.00 -- 5.00 Poster preview

    Dinner (not provided)

    7.30 -- 10.00 Poster session 1

  • Saturday January 6

    7.30 -- 9.00 Breakfast

    Morning 1: Boosting

    9.00 -- 9.30
    Boosting for Regression and Classification: Some Views from Analogy
    Wenxin Jiang

    9.30 -- 10.00
    Online Bagging and Boosting
    Nikunj Oza, Stuart Russell

    Coffee break

    Morning 2: Kernel methods

    10.30 -- 11.00
    An improved training algorithm for kernel Fisher discriminants
    Sebastian Mika, Alexander Smola, Bernhard Schoelkopf

    11.00 -- 11.30
    A Kernel Approach for Vector Quantization with Guaranteed Distortion Bounds
    Michael Tipping, Bernhard Schoelkopf

    11.30 -- 12.30 Poster preview

    Lunch (not provided)

    5.00 -- 7.30 Poster session 2

    7.30 -- 10.00 Conference banquet

  • Sunday, January 7

    7.30 -- 9.00 Breakfast

    Morning 1: Dynamic Bayesian networks

    9.00 -- 9.30
    Products of Hidden Markov Models
    Andrew Brown, Geoffrey Hinton

    9.30 -- 10.00
    Solving Hidden-Mode Markov Decision Problems
    Samuel Choi, Nevin Zhang, Dit-Yan Yeung

    10.00 -- 10.30
    Can the Computer Learn to Play Music Expressively?
    Christopher Raphael

    Coffee break

    Morning 2: Multiple Models

    11.00 -- 11.30
    Hyperparameters for Soft Bayesian Model Selection
    Adrian Corduneanu, Christopher Bishop

    11.30 -- 12.00
    Managing Multiple Models
    Hugh Chipman, Edward George, Robert McCulloch

    12.00 -- 12.15 Closing

    Papers in poster session 1 (Friday January 5)

    Image Decomposition and Tracking using Dynamic Positional Trees
    Amos Storkey, Christopher Williams

    Profile Likelihood in Directed Graphical Models from BUGS Output
    Malene Hojbjerre

    Stochastic System Monitoring and Control
    Gregory Provan

    Comparing Prequential Model Selection Criteria in Supervised Learning of Mixture Models
    Petri Myllymaki, Petri Kontkanen, Henry Tirri

    Variational Learning for Multi-Layer Networks of Linear Threshold Units
    Neil Lawrence

    Models for Conditional Probability Tables in Educational Assessment
    Russell Almond, DiBello Lou, Frank Jenkins, Robert Mislevy, Deniz Senturk,
    Linda Steinberg, Duanli Yan

    Discriminant Analysis on Dissimilarity Data : a New Fast Gaussian like Algorithm
    Guerin-Dugue Anne, Celeux Gilles

    Bayesian Support Vector Regression
    Martin Law, James Kwok

    Message Length as an Effective Ockham's Razor in Decision Tree Induction
    Scott Needham, David Dowe

    Dual perturb and combine algorithm
    Pierre Geurts

    Bagging and the Bayesian Bootstrap
    Merlise Clyde, Herbert Lee

    On the correspondence between partially-observable Markov decision processes and Bayes-adaptive Markov decision processes
    Michael Duff

    Learning mixtures of smooth nonuniform deformation fields for probabilistic image matching
    Nebojsa Jojic, Brendan Frey, Patrice Simard, David Heckerman

    Clustering in high dimensions: modular mixture models
    Hagai Attias

    Papers in poster session 2 (Saturday January 6)

    Learning in Bayesian networks with mixed variables
    Susanne Bottcher

    Instrumental Variable Estimation of Causal Influence without Linearity
    Richard Scheines, Greg Cooper

    On Parameter Priors for Discrete DAG Models
    Dan Geiger, Dmitry Rusakov

    The Efficient Propagation of Arbitrary Subsets of Beliefs in Discrete-Valued Bayesian Networks
    Duncan Smith

    Another look at sensitivity of Bayesian networks to imprecise probabilities
    Oscar Kipersztok, Hai-Qin Wang

    Some variations on variation independence.
    Philip Dawid

    On searching for optimal classifiers among Bayesian networks
    Robert Cowell

    Geographical clustering of cancer incidence by means of Bayesian networks and conditional Gaussian networks
    J. M. Pena, I. Izarzugaza, J. A. Lozano, E. Aldasoro and P. Larranaga

    Statistical Aspects of Stochastic Logic Programs
    James Cussens

    Temporal Matching under Uncertainty
    Ahmed Tawfik, Greg Scott

    Using Unsupervised Learning to Guide Resampling in Imbalanced Data Sets
    Adam Nickerson, Nathalie Japkowicz, Evangelos Milios

    Information-Theoretic Advisors in Invisible Chess
    Ariel Bud, Ingrid Zukerman, David Albrecht, Ann Nicholson

    A Non-Parametric EM-Style Algorithm for Filling-In Missing Values
    Rich Caruana

    Predicting with Variables Constructed from Univariate Temporal Sequences
    Mehmet Kayaalp, Greg Cooper, Gilles Clermont