Generalization Bounds via Online Learning

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

• Dr Gergely Neu, Universitat Pompeu Fabra
• Wednesday 08 March 2023, 14:00-15:00
• MR5, CMS Pavilion A.

If you have a question about this talk, please contact Prof. Ramji Venkataramanan.

Bounding the generalization error is one most fundamental problems in statistical learning theory. In this talk, I will present a new framework for deriving generalization bounds from the perspective of online learning. Specifically, we construct an online learning game called the Generalization Game, where an online learner is trying to compete with a fixed statistical learning algorithm in predicting the sequence of generalization gaps on a training set of i.i.d. data points. As I will show, this framework will allow us to recover a range of classic bounds including PAC -Bayes and generalizations thereof. (Based on joint work with Gabor Lugosi.)

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.