Alternate Learning and Compression Approaching R(D)

TL;DR

This paper explores the balance between exploration and exploitation in online learning by proposing a backward-adaptive lossy compression system that models this trade-off.

Contribution

It introduces a novel compression-based framework to analyze and optimize the exploration-exploitation trade-off in online learning.

Findings

Demonstrates the effectiveness of the proposed system in balancing exploration and exploitation.

Provides theoretical insights into the trade-off via compression metrics.

Suggests potential for improved long-term learning performance.

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.