Bandit Convex Optimisation Revisited: FTRL Achieves tildeO(t1/2) Regret
Not on the map. Why?
Abstract (arXiv)
We show that a kernel estimator using multiple function evaluations can be easily converted into a sampling-based bandit estimator with expectation equal to the original kernel estimate. Plugging such a bandit estimator into the standard FTRL algorithm yields a bandit convex optimisation algorithm that achieves tildeO(t1/2) regret against adversarial time-varying convex loss functions.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 5 of its 18 references that are in the map. First posted on arXiv 1 Feb 2023.
Builds on
5 of 18 references.
References · 5
- 2018Gaussian Processes and Kernel Methods: A Review on Connections and Equivalencescited by 188
- 2017Sobolev Norm Learning Rates for Regularized Least-Squares Algorithmcited by 113
- 2016Kernel-based methods for bandit convex optimizationcited by 63
- 2020Improved Regret for Zeroth-Order Adversarial Bandit Convex Optimisationcited by 33
- 2020Convergence Guarantees for Gaussian Process Means With Misspecified Likelihoods and Smoothnesscited by 29
Built on by
Not cited yet.