874f5e53d7ce44f65fbf27a7b9406983-Supplemental-Conference.pdf
–Neural Information Processing Systems
Ensemble sampling serves as apractical approximation to Thompson sampling when maintaining anexact posterior distribution overmodel parameters iscomputationally intractable. In this paper, we establish a regret bound that ensures desirable behavior when ensemble sampling isapplied tothe linear bandit problem.
Neural Information Processing Systems
Feb-10-2026, 12:31:59 GMT