Exploiting Higher Order Smoothness in Derivative-free Optimization and
Continuous Bandits

v1v2v3v4 (latest)

Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits

14 June 2020

Massimiliano Pontil

Alexandre B. Tsybakov

ArXiv (abs)PDF HTML

Papers citing "Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits"

13 / 13 papers shown

Title
Non-stationary Bandit Convex Optimization: A Comprehensive Study Xiaoqi Liu Dorian Baudry Julian Zimmert Patrick Rebeschini Arya Akhavan 60 0 0 03 Jun 2025
Gradient-free stochastic optimization for additive models A. Akhavan Alexandre B. Tsybakov 159 0 0 03 Mar 2025
Optimal estimators of cross-partial derivatives and surrogates of functions Matieyendou Lamboni 34 1 0 05 Jul 2024
How to Boost Any Loss Function Richard Nock Yishay Mansour 62 0 0 02 Jul 2024
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity Qian-long Yu Yining Wang Baihe Huang Qi Lei Jason D. Lee ODL 61 1 0 28 Jun 2024
Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm A. Akhavan Evgenii Chzhen Massimiliano Pontil Alexandre B. Tsybakov 54 11 0 03 Jun 2023
Estimating the minimizer and the minimum value of a regression function under passive design A. Akhavan Davit Gogolashvili Alexandre B. Tsybakov 109 0 0 29 Nov 2022
A gradient estimator via L1-randomization for online zero-order optimization with two point feedback A. Akhavan Evgenii Chzhen Massimiliano Pontil Alexandre B. Tsybakov 121 20 0 27 May 2022
Black-Box Generalization: Stability of Zeroth-Order Learning Konstantinos E. Nikolakakis Farzin Haddadpour Dionysios S. Kalogerias Amin Karbasi MLT 68 2 0 14 Feb 2022
Distributed Zero-Order Optimization under Adversarial Noise A. Akhavan Massimiliano Pontil Alexandre B. Tsybakov 85 20 0 01 Feb 2021
Smooth Bandit Optimization: Generalization to Hölder Space Yusha Liu Yining Wang Aarti Singh 60 10 0 11 Dec 2020
Continuum-Armed Bandits: A Function Space Perspective Shashank Singh 66 10 0 15 Oct 2020
A New One-Point Residual-Feedback Oracle For Black-Box Learning and Control Yan Zhang Yi Zhou Kaiyi Ji Michael M. Zavlanos 66 41 0 18 Jun 2020