Optimization of Smooth Functions With Noisy Observations: Local Minimax Rates

DOI10.1109/TIT.2019.2921985MaRDI QIDQ5211509zbMATH OpenOpenAlexFDO

Authors Yining Wang, Sivaraman Balakrishnan, Aarti Singh

Publication date 28 January 2020

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1803.08586

zbMATH Keywords

global optimizationunknown non-convex smooth function with noisy zeroth-order feedback

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Minimax problems in mathematical programming (90C47) Derivative-free methods and methods using generalized derivatives (90C56)

Abstract: We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the underlying function at different locations and receives noisy evaluations of function values at the queried points (i.e. the algorithm has access to zeroth-order information). Optimization performance is evaluated by the expected difference of function values at the estimated optimum and the true optimum. In contrast to the classical optimization setup, first-order information like gradients are not directly accessible to the optimization algorithm. We show that the classical minimax framework of analysis, which roughly characterizes the worst-case query complexity of an optimization algorithm in this setting, leads to excessively pessimistic results. We propose a local minimax framework to study the fundamental difficulty of optimizing smooth functions with adaptive function evaluations, which provides a refined picture of the intrinsic difficulty of zeroth-order optimization. We show that for functions with fast level set growth around the global minimum, carefully designed optimization algorithms can identify a near global minimizer with many fewer queries. For the special case of strongly convex and smooth functions, our implied convergence rates match the ones developed for zeroth-order convex optimization problems. At the other end of the spectrum, for worst-case smooth functions no algorithm can converge faster than the minimax rate of estimating the entire unknown function in the $el{l}_{i}nfty$-norm. We provide an intuitive and efficient algorithm that attains the derived upper error bounds.

Cited in

(4)

• Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm
• scientific article; zbMATH DE number 4078749 (Why is no real title available?)
• Derivative-free methods for policy optimization: guarantees for linear quadratic systems
• Optimal minimax rates against nonsmooth alternatives

This page was built for publication: Optimization of Smooth Functions With Noisy Observations: Local Minimax Rates

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5211509)