Optimistic No-regret Algorithms for Discrete Caching

TL;DR

This paper introduces new optimistic no-regret algorithms for online caching that leverage prediction oracles, achieving improved regret bounds over previous methods and extending to various caching scenarios.

Contribution

It develops a universal lower bound, proposes a suite of policies with trade-offs, and introduces the first comprehensive optimistic Follow-the-Perturbed leader policy for caching.

Findings

Proposed policies outperform existing online caching algorithms.

Achieve sublinear regret bounds proportional to oracle accuracy.

Validated effectiveness through experiments with real-world data.

Abstract

We take a systematic look at the problem of storing whole files in a cache with limited capacity in the context of optimistic learning, where the caching policy has access to a prediction oracle (provided by, e.g., a Neural Network). The successive file requests are assumed to be generated by an adversary, and no assumption is made on the accuracy of the oracle. In this setting, we provide a universal lower bound for prediction-assisted online caching and proceed to design a suite of policies with a range of performance-complexity trade-offs. All proposed policies offer sublinear regret bounds commensurate with the accuracy of the oracle. Our results substantially improve upon all recently-proposed online caching policies, which, being unable to exploit the oracle predictions, offer only $O(\sqrt{T})$ regret. In this pursuit, we design, to the best of our knowledge, the first comprehensive optimistic Follow-the-Perturbed leader policy, which generalizes beyond the caching problem. We also study the problem of caching files with different sizes and the bipartite network caching problem. Finally, we evaluate the efficacy of the proposed policies through extensive numerical experiments using real-world traces.