Improved regret for zeroth-order adversarial bandit convex optimisation

DOI10.4171/MSL/17zbMath1470.90080arXiv2006.00475OpenAlexW3157699871MaRDI QIDQ2035748

Tor Lattimore

Publication date: 25 June 2021

Published in: Mathematical Statistics and Learning (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.00475

zbMATH Keywords

online learningbandit convex optimisation

Mathematics Subject Classification ID

Convex programming (90C25) General considerations in statistical decision theory (62C05)

Related Items (1)

Stochastic zeroth-order discretizations of Langevin diffusions for Bayesian inference

Cites Work

• Unnamed Item
• Exploratory distributions for convex functions
• Isotropic surface area measures
• Kernel-based methods for bandit convex optimization
• Learning to Optimize via Posterior Sampling
• Asymptotic Geometric Analysis, Part I
• Prediction, Learning, and Games

This page was built for publication: Improved regret for zeroth-order adversarial bandit convex optimisation