Sepehr Assadi, Chen Wang. The Best Arm Evades: Near-optimal Multi-pass Streaming Lower Bounds for Pure Exploration in Multi-armed Bandits. In Shipra Agrawal 0001, Aaron Roth 0001, editors, The Thirty Seventh Annual Conference on Learning Theory, June 30 - July 3, 2023, Edmonton, Canada. Volume 247 of Proceedings of Machine Learning Research, pages 311-358, PMLR, 2024. [doi]
Abstract is missing.