Learning from compressed observations

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The problem of statistical learning is to construct a predictor of a random variable Y as a function of a related random variable X on the basis of an i.i.d. training sample from the joint distribution of (X, Y). Allowable predictors are drawn from some specified class, and the goal is to approach asymptotically the performance (expected loss) of the best predictor in the class. We consider the setting in which one has perfect observation of the X-part of the sample, while the Y-part has to be communicated at some finite bit rate. The encoding of the Y-values is allowed to depend on the X-values. Under suitable regularity conditions on the admissible predictors, the underlying family of probability distributions and the loss function, we give an information-theoretic characterization of achievable predictor performance in terms of conditional distortion-rate functions. The ideas are illustrated on the example of nonparametric regression in Gaussian noise.

Original languageEnglish (US)
Title of host publication2007 IEEE Information Theory Workshop, ITW 2007, Proceedings
Pages420-425
Number of pages6
DOIs
StatePublished - 2007
Event2007 IEEE Information Theory Workshop, ITW 2007 - Lake Tahoe, CA, United States
Duration: Sep 2 2007Sep 6 2007

Publication series

Name2007 IEEE Information Theory Workshop, ITW 2007, Proceedings

Other

Other2007 IEEE Information Theory Workshop, ITW 2007
CountryUnited States
CityLake Tahoe, CA
Period9/2/079/6/07

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Information Systems
  • Information Systems and Management

Fingerprint Dive into the research topics of 'Learning from compressed observations'. Together they form a unique fingerprint.

Cite this