MSRI Workshop on Nonlinear Estimation and Classification
Berkeley, California
March 19-29, 2001

Contributed Program

We received a large number of outstanding contributed papers. Below we list contributed talks talks and posters with a rough title for each session (these may change).

Contributed Talks
Week 1
Week 2
Monday Monday
Mixtures
  1. An ANOVA model for dependent random measures with an application to population models
    Maria DeIorio, Peter Mueller, Gary Rosner and Steven MacEachern
  2. Aspects of stochastic simulation based inference for some mixtures of latent structures
    Ernest Fokoue
  3. Clustering by partial mixture extimation
    David Scott
  4. Combining regression estimators
    Yuhong Yang
  5. Model complexity and model priors
    Angelika van der Linde
Wavelet methods/Multiresolution analyses
  1. Texture characterization and retrieval using steerable hidden Markov models
    Minh Do and Martin Vetterli
  2. Thresholding second generation wavelet coefficients for noisy, non-equispaced data
    Maarten Jansen
  3. A multiresolution analysis for statistical likelihoods: Theory and methods
    Eric Kolaczyk and Robert Nowak
  4. Best adaptive tiling in a rate-distortion sense
    Rahul Shukla, Minh Do and Martin Vetterli
  5. Multi-resolution properties of semi-parametric volatility models
    Enrico Capobianco
Tuesday Tuesday
SVM/Machine Learning
  1. Adaptive kernels for SV classification
    Robert Brubidge
  2. Unsupervised sparse regression
    Mario A. T. Figueiredo
  3. Instability in nonlinear estimation and classification
    Steve Ellis
Clustering
  1. Data compression and statistical inference
    Jorg Rahnenfuhrer
  2. Local curved gaussian models
    Juan Lin
  3. "Compressing and analyzing massive geophysical data sets by Monte Carlo extended ECVQ"
    Amy Braverman
  4. Clustering via pulse-coupled oscillators
    Mohamed Ben Hadi Rhouma
Wednesday Wednesday
Splines
  1. Logspline density estimation with free-knot splines
    Charles Kooperberg and Charles Stone
  2. Adaptive splines and genetic algorithms with an application to classification
    Jennifer Pittman
  3. Mixed-effects multivariate adaptive splines models: An automated procedure for fitting longitudinal data and growth curves
    Heping Zhang
  4. Bayesian mixture splines for spatially adaptive
    Sally Wood
Bioinformatics
  1. Computationally intensive statistical methods for microarray based drug discovery
    Katherine Pollard and Mark van der Laan
  2. Active Learning of Bayes Net Structure with Applications to Gene Knockout Experiment Design
    K. Murphy
  3. Using robust and resistant regression analysis (MM-estimator) to find differentially expressed genes in microarray data
    Alexander Loguinov, Rus Yukhananov, Christopher Vulpe and Saira Mian
  4. "Logic Regression"
    Ingo Ruczinski, Charles Kooperberg and Michael L. LeBlanc
Thursday Thursday
Non-linear systems/Time series
  1. Denoising deterministic time series
    Andrew Nobel
  2. A statistical approach to quantifying the predictability of noisy nonlinear systems
    Barbara Bailey
  3. Looking for nonlinearities in the large scale dynamics of the atmosphere
    Claudia Tebaldi
  4. Non-stationary, nonlinear classification and model selection
    Nando DeFreitas
  5. Semiparametric estimation of the long-memory parameter in farima models
    Ashis Gangopadhyay and Kin Cheung
Dimension Reduction
  1. High dimension - low sample size data analysis
    Steve Marron
  2. A global geometric framework for nonlinear dimensionality reduction
    Joshua Tenenbaum
  3. Multivariate optimal scaling techniques for the analysis of large and complicated data sets
    Jacqueline J. Meulman
  4. Construction of low dimensional DME reaction state space trajectories
    Nelson Butuk
Friday
Nonparametric regression and classification: Theory
  1. Bounding generalization error of aggregate classifiers through empirical margin distributions
    Gilles Blanchard
  2. Risk bounds for CART regression trees
    Servane Gey and Elodie Nedelec
  3. Nonlinear function learning and classification using optimal radial basis function networks
    Adam Kryzak
  4. On adaptive estimation by neural nets type estimators
    Ludger Ruschendorf
  5. Fast rates and adaptation in nonparametric classification
    Alexandre Tsybakov
Contributed Posters
Wednesday, March 21 Tuesday, March 27
  1. Multivariate survival trees by goodness of split
    Xiao-Gang Su and Juanjuan Fan
  2. A local Weibull model for survival data
    Clive Hoggart
  3. A general spline smoothing algorithm
    Chunfeng Huang
  4. On a nonlinear method of function recovering: The vertical regression approach
    M. Pawlak and E. Rafajlowicz
  5. Function approximation and classification by linguistic if-then rules
    Hisao Ishibuchi, Tomoharu Nakashima, Daisuke Takeuchi and Takashi Yamamoto
  6. Asymptotic investigations of support vector regression with noiseless and noisy data
    Christina Andersson and G. Kroisandt
  7. Structural learning for Bayesian networks with hidden variables
    Raffaella Settimi
  8. Comparing classification accuracy of data ensemble and clustering algorithms based on Taguchi design
    So Young Sohn and Hyung Won Shin
  9. Using random trees to identify chemical structures associated with biological activity
    Joseph Verducci, Michael Flinger, Paul Blower and Jeffrey Bjoraker
  1. Problems in inference after model selection
    Hannes Leeb and Benedikt M. Potscher
  2. Neural network vs. discriminant analysis in detecting financial distress among major Australian companies
    S. Ganesalingam
  3. Nonlinear methods in data mining: Comparison of 2D wavelet de-noising methods
    I. K. Fodor and C. Kamath
  4. Invariant variational principle for model-based interpolation of high dimensional clustered data
    R. C. Venkatesan
  5. Classification of voiceless stop consonants using time-frequency based representations
    Ewa Lukasik
  6. Behavioral models of microwave circuits using a priori information
    Nicholas B. Tufillaro and David M. Walker
  7. Some Improvements in the evaluation of methods to rank alternatives
    Joaquim Costa, Carlos Soares and Pavel Brazdil