Near Optimal Memory-Regret Tradeoff for Online Learning

March 03, 2023 Β· Declared Dead Β· πŸ› IEEE Annual Symposium on Foundations of Computer Science

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Binghui Peng, Aviad Rubinstein arXiv ID 2303.01673 Category cs.DS: Data Structures & Algorithms Cross-listed cs.AI, cs.LG Citations 11 Venue IEEE Annual Symposium on Foundations of Computer Science Last Checked 4 months ago
Abstract
In the experts problem, on each of $T$ days, an agent needs to follow the advice of one of $n$ ``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 $o(T)$ 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 $\sqrt{n}$ memory is both necessary and sufficient for obtaining $o(T)$ regret.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Data Structures & Algorithms

Died the same way β€” πŸ‘» Ghosted