Answers are grounded in this paper and cite their sources.
We consider the adversarial convex bandit problem and we build the first poly(T)-time algorithm with poly(n) √T-regret for this problem. To do so we introduce three new ideas in the derivative-free optimization
No takes yet. Share an insight, caveat, or question.
Bubeck et al. (2017) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: