University of Cambridge > Talks.cam > Applied and Computational Analysis > PDE continuum limits for prediction with expert advice

  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

ℹ️ Information

PDE continuum limits for prediction with expert advice

Download to your calendar using vCal

  • UserJeff Calder (University of Minnesota)
  • ClockThursday 06 June 2019, 15:00-16:00
  • HouseMR 14.

If you have a question about this talk, please contact Matthew Thorpe .

Prediction with expert advice refers to a class of machine learning problems that is concerned with how to optimally combine advice from multiple experts whose prediction qualities may vary greatly. We study a stock prediction problem with history-dependent experts and an adversarial (worst-case) market, posing the problem as a repeated two-player game. We prove that when the game is played for a long time, the discrete value function converges in the continuum to the solution of a nonlinear parabolic partial differential equation (PDE). This allows us to identify asymptotically optimal strategies for the player and market.

This talk is part of the Applied and Computational Analysis series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Addenbrooke’s Clinical School Seminar Room 6 please see http://www.trophoblast.cam.ac.uk/info/seminar.shtml for directions LR3A, CUED Music & Mediation Pavilion , Lucy Cavendish College, Cambridge CB3 0BU.

Other talks

Cambridge RNA Club - ONLINE A novel hereditary encephalopathy in four related Labrador Retrievers associated with a missense variant in the ALDH5A1 gene’ Title and abstract tba Title to be confirmed Dr Dinis Calado, Senior Group Leader, Immunity and Cancer Laboratory, the Francis Crick Institute Proteomics: Expression Analysis and Subcellular Localisation
 

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