About
The present workshop addresses the problem of predicting a - binary - label Y from given the feature X. A procedure for classification is to be learned from a training set (X1, Y1) , ... , (Xn , Yn ). In the statistical literature on classification, the training set is traditionally seen as an i.i.d. sample from the distribution P of (X,Y), but one otherwise does not assume any a priori knowledge on P. Theoretical results have been derived that hold no matter what P is, which typically means that such results concentrate on worst cases. There are various reasons to step aside from this so-called black box approach. For example, the by now generally accepted rule regression is harder that classification" has led to a bad name for certain "plug in" methods, although under distributional assumptions the latter are at least competitive with
direct" methods. Moreover, theoretical results for a case where P is assumed to be within a small class, can give benchmarks on what one may hope for. Also, procedures which adapt to properties of P need further exploration. These procedures are designed to work well in case one is "lucky", and are as such also inspired by having certain distributional assumptions in the back of ones mind. It moreover is often quite reasonable to assume some knowledge of the marginal distribution of X.
Videos
Lectures

On minimax estimation of infinite dimensional vector of binomial proportions
Feb 25, 2007
·
3506 views

Mistake bounds and risk bounds for on-line learning algorithms
Feb 25, 2007
·
3138 views

The Limit of One-Class SVM
Feb 25, 2007
·
9864 views

How classifieres can be use to solve any reasonable loss
Feb 25, 2007
·
3242 views

Penalized empirical risk minimization in the estimation of thresholds
Feb 25, 2007
·
2945 views

Generalization Error under Covariate Shift Input-Dependent Estimation of General...
Feb 25, 2007
·
3659 views

Suboptimality of MDL and Bayes in Classification under Misspecification
Feb 25, 2007
·
3216 views

Unified Loss Function and Estimating Function Based Learning
Feb 25, 2007
·
3607 views

On-line learning competitive with reproducing kernel Hilbert spaces
Feb 25, 2007
·
4080 views

Robustness properties of support vector machines and related methods
Feb 25, 2007
·
4884 views

Faster Rates via Active Learning
Feb 25, 2007
·
3747 views

Universal Principles, Approximation and Model Choices
Feb 25, 2007
·
2941 views

Nonparametric Tests between Distributions
Feb 25, 2007
·
7398 views

PERFORMANCE BOUNDS FOR KERNEL PCA
Apr 12, 2007
·
5378 views
Impromptu Session

Anti-Learning Signature in Biological Classification
Apr 12, 2007
·
3036 views

Agnostic Active learning
Apr 12, 2007
·
3636 views

Generalization to Unseen Cases: (No) Free Lunches and Good-Turing estimation
Apr 12, 2007
·
3367 views