Parameter-free Online Linear Optimization with Side Information via Universal Coin Betting

TL;DR

This paper introduces parameter-free online linear optimization algorithms that adapt to adversarial sequences using side information, combining coin betting and universal compression techniques for improved performance.

Contribution

It develops a novel framework integrating coin betting and information-theoretic compression to handle structured side information in online optimization.

Findings

Algorithms adapt to side information with tree structures.

Achieves optimal performance over all adaptive algorithms with bounded complexity.

Refines context-tree weighting for efficient computation.

Abstract

A class of parameter-free online linear optimization algorithms is proposed that harnesses the structure of an adversarial sequence by adapting to some side information. These algorithms combine the reduction technique of Orabona and P{\'a}l (2016) for adapting coin betting algorithms for online linear optimization with universal compression techniques in information theory for incorporating sequential side information to coin betting. Concrete examples are studied in which the side information has a tree structure and consists of quantized values of the previous symbols of the adversarial sequence, including fixed-order and variable-order Markov cases. By modifying the context-tree weighting technique of Willems, Shtarkov, and Tjalkens (1995), the proposed algorithm is further refined to achieve the best performance over all adaptive algorithms with tree-structured side information of a given maximum order in a computationally efficient manner.