Simple and cumulative regret for continuous noisy optimization

DOI10.1016/J.TCS.2015.09.032MaRDI QIDQ905845zbMATH OpenOpenAlexFDO

Authors Sandra Astete-Morales, Marie-Liesse Cauwet, Jialin Liu, Olivier Teytaud

Publication date 28 January 2016

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2015.09.032

zbMATH Keywords

runtime analysisnoisy optimization

Mathematics Subject Classification ID

Stochastic programming (90C15)

Recommendations

• Evolution strategies with additive noise: a convergence rate lower bound
• Handling expensive optimization with large noise
• A direct search algorithm for optimization with noisy function evaluations
• Approximate implementations of pure random search in the presence of noise
• Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods

Cites work

• scientific article; zbMATH DE number 823069 (Why is no real title available?)
• A Continuous Kiefer-Wolfowitz Procedure for Random Processes
• A Family of Variable-Metric Methods Derived by Variational Means
• A Stochastic Approximation Method
• A new approach to variable metric algorithms
• Adaptive stochastic approximation by the simultaneous perturbation method
• Conditioning of Quasi-Newton Methods for Function Minimization
• Extremal Eigenvalues of Real Symmetric Matrices with Entries in an Interval
• Feedback and Weighting Mechanisms for Improving Jacobian Estimates in the Adaptive Simultaneous Perturbation Algorithm
• Handling expensive optimization with large noise
• Introduction to Stochastic Search and Optimization
• Lower rate of convergence for locating a maximum of a function
• Noisy optimization complexity under locality assumption
• On the Kiefer-Wolfowitz approximation method
• Pure exploration in finitely-armed and continuous-armed bandits
• Stochastic Approximation of Minima with Improved Asymptotic Speed
• Stochastic Estimation of the Maximum of a Regression Function
• The Convergence of a Class of Double-rank Minimization Algorithms
• The NEWUOA software for unconstrained optimization without derivatives
• Viability theory

Cited in

(5)

• Sorting by swaps with noisy comparisons
• Algorithm portfolios for noisy optimization
• Robust randomized optimization with \(k\) nearest neighbors
• Evolution strategies with additive noise: a convergence rate lower bound
• Default policies for global optimisation of noisy functions with severe noise

Describes a project that uses

Uses Software

• NEWUOA

This page was built for publication: Simple and cumulative regret for continuous noisy optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q905845)