University of Cambridge > Talks.cam > Statistics > Efficient and Parsimonious Agnostic Active Learning

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹī¸ Information

Efficient and Parsimonious Agnostic Active Learning

Download to your calendar using vCal

If you have a question about this talk, please contact Quentin Berthet .

We develop a new active learning algorithm for the streaming setting satisfying three important properties: 1) It provably works for any classifier representation and classification problem including those with severe noise. 2) It is efficiently implementable with an ERM oracle. 3) It is more aggressive than all previous approaches satisfying 1 and 2. To do this we create an algorithm based on a newly defined optimization problem and analyze it. We also conduct the first experimental analysis of all efficient agnostic active learning algorithms, evaluating their strengths and weaknesses in different settings.

This is joint work with Tzu-Kuo Huang, John Langford and Rob Schapire at Microsoft Research.

This talk is part of the Statistics series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Hybrid: in-person in Cambridge & online via Teams https://live.remo.co/e/fluids-group-seminar BBMS

Other talks

In conversation: Louis Herns Marcelin and Ola Osman on legacies of enslavement and contemporary violence in Liberia and Haiti Using numerical simulations for solving spectral geometry problems New insights on the turbulent energy cascade from non-equilibrium statistical mechanics Climate, uncertainty, and the slippery measurement of Antarctic ice Title TBC Title to be confirmed
 

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