#machine learning
Nov 2025
Fooling Algorithms in Non-Stationary Bandits using Belief Inertia
The proof combines two deterministic obstructions: a stationary small-gap instance that makes repeated forgetting costly, and a one-breakpoint instance that creates a strict post-change index lock that yields an algorithmic separation.
Gal Mendelson, Eyal Tadmor
· arXiv.org · 0 citations