University of Cambridge > Talks.cam > Information Theory Seminar > Generalization Bounds via Online Learning

  Browse A-Z

Log in

Googledetails Microsoftdetails

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Generalization Bounds via Online Learning

Download to your calendar using vCal

  • UserDr Gergely Neu, Universitat Pompeu Fabra Speaker website
  • ClockWednesday 08 March 2023, 14:00-15:00
  • HouseMR5, 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:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 8881.54032258 kWh Average on weekdays: 9024.83797909 kWh Centre for Mathematical Sciences, Meeting Room 3

Other talks

Secrets of the Surface: The Mathematical Vision of Maryam Mirzakhani ( EDI Film Screening) Quantifying the unquantifiable? Assessing the importance of almsgiving in early modern France and Spain Polar Oceans Seminar Talk Why people with schizophrenia die earlier? Mortality and accelerated ageing Teams Announced Together Now: Cooperation and Collaboration in Social Art Practice
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity