Learning theory for conditional risk minimization Conference Paper


Author(s): Zimin, Alexander; Lampert, Christoph
Title: Learning theory for conditional risk minimization
Title Series: PMLR
Affiliation IST Austria
Abstract: In this work we study the learnability of stochastic processes with respect to the conditional risk, i.e. the existence of a learning algorithm that improves its next-step performance with the amount of observed data. We introduce a notion of pairwise discrepancy between conditional distributions at different times steps and show how certain properties of these discrepancies can be used to construct a successful learning algorithm. Our main results are two theorems that establish criteria for learnability for many classes of stochastic processes, including all special cases studied previously in the literature.
Conference Title: AISTATS: Artificial Intelligence and Statistics
Volume: 54
Conference Dates: April 20 - 22, 2017
Conference Location: Fort Lauderdale, FL, USA
Publisher: JMLR, Inc. and Microtome Publishing  
Date Published: 2017-01-01
Start Page: 213
End Page: 222
Copyright Statement: Copyright 2017 by the author(s)
Sponsor: FP7/2007-2013 ERC grant agreement no 308036
URL:
Open access: yes (OA journal)
IST Austria Authors
  1. Christoph Lampert
    87 Lampert
  2. Alexander Zimin
    2 Zimin