Alternate Learning and Compression Approaching R(D)

TL;DR

This work proposes to study the trade-off between exploration and exploitation through a backward-adaptive lossy compression system, which exhibits a "natural" trade-off between exploration and exploitation.

Abstract

The inherent trade-off in on-line learning is between exploration and exploitation. A good balance between these two (conflicting) goals can achieve a better long-term performance. Can we define an optimal balance? We propose to study this question through a backward-adaptive lossy compression system, which exhibits a "natural" trade-off between exploration and exploitation.