English

Minimax Learning for Remote Prediction

Information Theory 2021-01-19 v2 math.IT

Abstract

The classical problem of supervised learning is to infer an accurate predictor of a target variable YY from a measured variable XX by using a finite number of labeled training samples. Motivated by the increasingly distributed nature of data and decision making, in this paper we consider a variation of this classical problem in which the prediction is performed remotely based on a rate-constrained description MM of XX. Upon receiving MM, the remote node computes an estimate Y^\hat Y of YY. We follow the recent minimax approach to study this learning problem and show that it corresponds to a one-shot minimax noisy source coding problem. We then establish information theoretic bounds on the risk-rate Lagrangian cost and a general method to design a near-optimal descriptor-estimator pair, which can be viewed as a rate-constrained analog to the maximum conditional entropy principle used in the classical minimax learning problem. Our results show that a naive estimate-compress scheme for rate-constrained prediction is not in general optimal.

Keywords

Cite

@article{arxiv.1806.00071,
  title  = {Minimax Learning for Remote Prediction},
  author = {Cheuk Ting Li and Xiugang Wu and Ayfer Ozgur and Abbas El Gamal},
  journal= {arXiv preprint arXiv:1806.00071},
  year   = {2021}
}

Comments

10 pages, 4 figures, presented in part at ISIT 2018

R2 v1 2026-06-23T02:15:19.510Z