Variations of the Expectation due to Changes in the Measure: Applications to Generalization and Game Theory

Add to your list(s) Download to your calendar using vCal

• Dr Samir Perlaza, INRIA
• Wednesday 26 February 2025, 14:00-15:00
• MR5, CMS Pavilion A.

If you have a question about this talk, please contact Dr Amir R. Asadi.

In this talk, closed-form expressions are presented for the variation of the expectation of a given function due to changes in the probability measure used for the expectation. Two immediate applications are found in statistical machine learning and game theory. The former leads to closed-form expressions for the generalization error of machine learning algorithms. The latter leads to exact characterizations of the gain/loss of players involved in a zero-sum game in which a player allows its opponent to observe its action up to certain distortion. In both cases, these characterizations reveal interesting connections with Gibbs probability measures, mutual information, and lautum information.

This talk is part of the Information Theory Seminar series.

This talk is included in these lists:

• All CMS events
• All Talks (aka the CURE list)
• CMS Events
• DPMMS Lists
• DPMMS info aggregator
• DPMMS lists
• Hanchen DaDaDash
• Information Theory Seminar
• Interested Talks
• MR5, CMS Pavilion A
• School of Physical Sciences
• Statistical Laboratory info aggregator
• bld31

Note that ex-directory lists are not shown.