An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
From MaRDI portal
Publication:5361319
zbMath1440.90049arXiv1507.08752MaRDI QIDQ5361319
Publication date: 27 September 2017
Full work available at URL: https://arxiv.org/abs/1507.08752
Related Items (28)
New First-Order Algorithms for Stochastic Variational Inequalities ⋮ Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems ⋮ A theoretical and empirical comparison of gradient approximations in derivative-free optimization ⋮ Finite Difference Gradient Approximation: To Randomize or Not? ⋮ Zeroth-order algorithms for stochastic distributed nonconvex optimization ⋮ An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization ⋮ Gradient-free federated learning methods with \(l_1\) and \(l_2\)-randomization for non-smooth convex stochastic optimization problems ⋮ Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact ⋮ Non-smooth setting of stochastic decentralized convex optimization problem over time-varying graphs ⋮ Sign stochastic gradient descents without bounded gradient assumption for the finite sum minimization ⋮ Zeroth-order feedback optimization for cooperative multi-agent systems ⋮ Re-thinking high-dimensional mathematical statistics. Abstracts from the workshop held May 15--21, 2022 ⋮ Unnamed Item ⋮ Adaptive sampling quasi-Newton methods for zeroth-order stochastic optimization ⋮ Unifying framework for accelerated randomized methods in convex optimization ⋮ Technical Note—Nonstationary Stochastic Optimization Under Lp,q-Variation Measures ⋮ Adaptive Catalyst for Smooth Convex Optimization ⋮ Recent theoretical advances in decentralized distributed convex optimization ⋮ Smoothed functional-based gradient algorithms for off-policy reinforcement learning: a non-asymptotic viewpoint ⋮ An accelerated directional derivative method for smooth stochastic convex optimization ⋮ On the upper bound for the expectation of the norm of a vector uniformly distributed on the sphere and the phenomenon of concentration of uniform measure on the sphere ⋮ Gradient-Free Methods with Inexact Oracle for Convex-Concave Stochastic Saddle-Point Problem ⋮ A new one-point residual-feedback oracle for black-box learning and control ⋮ Derivative-free optimization methods ⋮ Distributed online bandit optimization under random quantization ⋮ Unnamed Item ⋮ Noisy zeroth-order optimization for non-smooth saddle point problems ⋮ One-point gradient-free methods for smooth and non-smooth saddle-point problems
This page was built for publication: An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
