Stochastic zeroth order descent with structured directions

DOI10.1007/s10589-024-00616-1MaRDI QIDQ6642789

Marco Rando, Cesare Molinari, Silvia Villa, Lorenzo Rosasco

Publication date: 25 November 2024

Published in: Computational Optimization and Applications (Search for Journal in Brave)

zbMATH Keywords

stochastic optimizationconvex optimizationfinite differencesderivative-free optimizationblack-box optimizationzeroth-order optimization

Mathematics Subject Classification ID

Convex programming (90C25) Nonlinear programming (90C30) Derivative-free methods and methods using generalized derivatives (90C56) Stochastic programming (90C15) Mathematical programming (90Cxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• How to generate random matrices from the classical compact groups
• On the optimal order of worst case complexity of direct search
• Gaussian process bandits with adaptive discretization
• UOBYQA: unconstrained optimization by quadratic approximation
• Stochastic mesh adaptive direct search for blackbox optimization using probabilistic estimates
• A stochastic subspace approach to gradient-free optimization in high dimensions
• Expected complexity analysis of stochastic direct-search
• A theoretical and empirical comparison of gradient approximations in derivative-free optimization
• A one-bit, comparison-based gradient estimator
• Random gradient-free minimization of convex functions
• A direct search algorithm for optimization with noisy function evaluations
• Smoothing and worst-case complexity for direct-search methods in nonsmooth optimization
• Randomized Smoothing for Stochastic Optimization
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
• Introduction to Derivative-Free Optimization
• Introduction to Stochastic Search and Optimization
• Stochastic Three Points Method for Unconstrained Smooth Minimization
• Trends in Consensus-Based Optimization
• Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Direct Search Based on Probabilistic Descent
• Stochastic Estimation of the Maximum of a Regression Function
• On a Stochastic Approximation Method
• Worst case complexity of direct search under convexity
• Scalable subspace methods for derivative-free nonlinear least-squares optimization
• Zeroth-order optimization with orthogonal random directions
• Direct Search Based on Probabilistic Descent in Reduced Spaces

This page was built for publication: Stochastic zeroth order descent with structured directions