Notions of Complexity: Information-theoretic, Computational and Statistical Approaches Workshop, Eindhoven 2004

Notions of Complexity: Information-theoretic, Computational and Statistical Approaches Workshop, Eindhoven 2004

6 Lectures · Oct 6, 2004

About

The theoretical analysis of systems that learn from data has been an important topic of study in statistics, machine learning, and information theory. In all these paradigms, distinct methods have been developed to deal with inference when the models under consideration can be arbitrarily large. Recently, there has been a fruitful cross-fertilization of ideas and proof techniques. To give but one example, very recently, minimax optimal convergence rates of the information-theoretic MDL method were proved using ideas from the - computational - PAC-Bayesian paradigm and - statistical - empirical process techniques. The goal of this workshop is to bring together leading theoreticians to allow them to debate, compare and cross-fertilise ideas from these distinct inductive principles. At the workshop, we will establish a PASCAL special interest group for `merging computational and information-theoretic learning with statistics'.

Related categories

Uploaded videos:

Lectures

video-img
57:31

Empirical Bayesian test for the smoothness

Eduard Belitser

Feb 25, 2007

 · 

4266 Views

Lecture

Lectures

video-img
01:01:43

The Complexity of Learning Verification

John Langford

Feb 25, 2007

 · 

4000 Views

Lecture
video-img
51:15

Support vector machines loss with l1 penalty

Sara van de Geer

Feb 25, 2007

 · 

5934 Views

Lecture
video-img
01:02:54

Convergence of MDL and Bayesian Methods

Tong Zhang

Feb 25, 2007

 · 

4623 Views

Lecture
video-img
55:24

Fast Learning Rates for Support Vector Machines

Ingo Steinwart

Feb 25, 2007

 · 

5108 Views

Lecture
video-img
01:01:52

Universal Coding/Prediction and Statistical (In)consistency of Bayesian inferenc...

Peter Grünwald

Feb 25, 2007

 · 

4608 Views

Lecture