BIDS algorithm for batched single-index global MAB with covariates achieves minimax-optimal regret rates when a pilot direction is accurate and K is fixed, avoiding the curse of dimensionality.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Simulations show physical neural networks need nonlinearity, amplification, and suppression for learning, with physically plausible circuit designs presented.
citing papers explorer
-
Batched Single-Index Global Multi-Armed Bandits with Covariates
BIDS algorithm for batched single-index global MAB with covariates achieves minimax-optimal regret rates when a pilot direction is accurate and K is fixed, avoiding the curse of dimensionality.