Universal Caching

TL;DR

This paper introduces a universal online caching policy that minimizes regret against a flexible, finite-state benchmark, achieving the first data-dependent regret bounds in this setting using information-theoretic methods.

Contribution

It proposes an efficient universal caching algorithm with sub-linear regret bounds, extending the analysis to finite-state benchmarks and applying information theory techniques.

Findings

First data-dependent regret bounds for universal caching

Achieves sub-linear regret in non-stationary settings

Combines online caching with Lempel-Ziv parsing for improved analysis

Abstract

In learning theory, the performance of an online policy is commonly measured in terms of the static regret metric, which compares the cumulative loss of an online policy to that of an optimal benchmark in hindsight. In the definition of static regret, the action of the benchmark policy remains fixed throughout the time horizon. Naturally, the resulting regret bounds become loose in non-stationary settings where fixed actions often suffer from poor performance. In this paper, we investigate a stronger notion of regret minimization in the context of online caching. In particular, we allow the action of the benchmark at any round to be decided by a finite state machine containing any number of states. Popular caching policies, such as LRU and FIFO, belong to this class. Using ideas from the universal prediction literature in information theory, we propose an efficient online caching policy with a sub-linear regret bound. To the best of our knowledge, this is the first data-dependent regret bound known for the caching problem in the universal setting. We establish this result by combining a recently-proposed online caching policy with an incremental parsing algorithm, namely Lempel-Ziv '78. Our methods also yield a simpler learning-theoretic proof of the improved regret bound as opposed to the involved problem-specific combinatorial arguments used in the earlier works.