Conference Schedule
Friday, October 19
8:15 - 8:45 Registartion: Blocker 1st floor
8:45 - 9:00 Opening remarks
9:00 - 9:50 Steve Smale:
Vision and learning
10:00 - 10:30
Coffee break:
Blocker 112
10:30 - 11:10 Stephane Boucheron:
A poor man's Wilks phenomenon
11:20 - 12:00 Alessandro Verri:
Regularization Algorithms for Learning
2:00 - 2:50 Patrick Wolfe:
The Nystrom Extension and Spectral Methods in Learning
3:00 - 3:30
Coffee break:
Blocker 112
3:30 - 4:10 Ingo Steinwart:
Approximation Theoretical Questions for Support Vector Machine
4:20 - 5:00 Vladimir Temlyakov:
Universality and Lebesgue inequalities in approximation and estimation
Saturday, October 20
9:00 - 9:50 Ingrid Daubechies:
Convergence results and counterexamples for AdABoost
and related algorithms
10:00 - 10:30
Coffee break:
Blocker 112
10:30 - 11:10 Nira Dyn:
Two algorithms for adaptive approximation of bivariate functions
by piecewise linear polynomials on triangulations
11:20 - 12:00 Vladimir Koltchinskii:
Sparse Recovery Problems in Learning Theory
2:00 - 2:50 Dominique Picard:
A 'Frame-work' in Learning Theory
3:00 - 3:30
Coffee break:
Blocker 112
3:30 - 4:10 Gilles Blanchard:
Resampling-based confidence regions in high dimension
from a non-asymptotic point of view
4:20 - 5:00 Ding-Xuan Zhou:
Learnability of Gaussians with Flexible Variances
Sunday, October 21
9:00 - 9:50 Albert Cohen:
Matching vs. basis pursuit for approximation and learning: a comparison
10:00 - 10:30
Coffee break:
Blocker 112
10:30 - 11:10 Christoph Schwab:
Elliptic PDEs with random field input -- numerical analysis
of forward solvers and of goal oriented input learning
11:20 - 12:00 Lee Jones:
Finite sample minimax estimation, fusion in machine learning,
and overcoming t
he curse of dimensionality
1:00 - 1:50 Tomaso Poggio:
Learning: neuroscience and engineering applications
2:00 - 2:40 Maya Gupta:
Functional Bregman Divergence, Bayesian Estimation of Distributions
and Completely Lazy Classifiers