13
10

Near Optimal Memory-Regret Tradeoff for Online Learning

Abstract

In the experts problem, on each of TT days, an agent needs to follow the advice of one of nn ``experts''. After each day, the loss associated with each expert's advice is revealed. A fundamental result in learning theory says that the agent can achieve vanishing regret, i.e. their cumulative loss is within o(T)o(T) of the cumulative loss of the best-in-hindsight expert. Can the agent perform well without sufficient space to remember all the experts? We extend a nascent line of research on this question in two directions: \bullet We give a new algorithm against the oblivious adversary, improving over the memory-regret tradeoff obtained by [PZ23], and nearly matching the lower bound of [SWXZ22]. \bullet We also consider an adaptive adversary who can observe past experts chosen by the agent. In this setting we give both a new algorithm and a novel lower bound, proving that roughly n\sqrt{n} memory is both necessary and sufficient for obtaining o(T)o(T) regret.

View on arXiv
Comments on this paper