Online Learning with Limited Information in the Sliding Window Model

TL;DR

This paper develops algorithms for the experts problem in the sliding window model, achieving near-optimal regret with minimal memory and query complexity, and extends results to bandit problems in data streams.

Contribution

It introduces memory-efficient algorithms for sliding window experts problems with multiple queries, and provides the first sublinear regret algorithm for bandit problems in streaming settings.

Findings

Achieves near-optimal regret with 2 queries and polylogarithmic memory.

Provides exponential memory improvement over previous interval regret algorithms.

First sublinear regret algorithm for bandit problems in streaming with polylogarithmic memory.

Abstract

Motivated by recent work on the experts problem in the streaming model, we consider the experts problem in the sliding window model. The sliding window model is a well-studied model that captures applications such as traffic monitoring, epidemic tracking, and automated trading, where recent information is more valuable than older data. Formally, we have $n$ experts, $T$ days, the ability to query the predictions of $q$ experts on each day, a limited amount of memory, and should achieve the (near-)optimal regret $\sqrt{nW}\text{polylog}(nT)$ regret over any window of the last $W$ days. While it is impossible to achieve such regret with $1$ query, we show that with $2$ queries we can achieve such regret and with only $\text{polylog}(nT)$ bits of memory. Not only are our algorithms optimal for sliding windows, but we also show for every interval $\mathcal{I}$ of days that we achieve $\sqrt{n|\mathcal{I}|}\text{polylog}(nT)$ regret with $2$ queries and only $\text{polylog}(nT)$ bits of memory, providing an exponential improvement on the memory of previous interval regret algorithms. Building upon these techniques, we address the bandit problem in data streams, where $q=1$, achieving $n T^{2/3}\text{polylog}(T)$ regret with $\text{polylog}(nT)$ memory, which is the first sublinear regret in the streaming model in the bandit setting with polylogarithmic memory; this can be further improved to the optimal $\mathcal{O}(\sqrt{nT})$ regret if the best expert's losses are in a random order.