Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise

In this paper, we develop convergence analysis of a modified line search method for objective functions whose value is computed with noise and whose gradient estimates are inexact and possibly random. The noise is assumed to be bounded in absolute value without any additional assumptions. We extend the framework based on stochastic methods from [Cartis and Scheinberg, 2018] which was developed to provide analysis of a standard line search method with exact function values and random gradients to the case of noisy function. We introduce a condition on the gradient which when satisfied with some sufficiently large probability at each iteration, guarantees convergence properties of the line search method. We derive expected complexity bounds for convex, strongly convex and nonconvex functions.

[1]  R. Carter.  On the global convergence of trust region algorithms using inexact gradient information , 1991 .

[2]  Stephen J. Wright,et al.  Numerical Optimization (Springer Series in Operations Research and Financial Engineering) , 2000 .

[3]  Yurii Nesterov,et al.  Introductory Lectures on Convex Optimization - A Basic Course , 2014, Applied Optimization.

[4]  Adam Tauman Kalai,et al.  Online convex optimization in the bandit setting: gradient descent without a gradient , 2004, SODA '05.

[5]  Stefan M. Wild,et al.  Benchmarking Derivative-Free Optimization Algorithms , 2009, SIAM J. Optim..

[6]  C. T. Kelley,et al.  Implicit Filtering , 2011 .

[7]  Jorge Nocedal,et al.  Sample size selection in optimization methods for machine learning , 2012, Math. Program..

[8]  Yurii Nesterov,et al.  Random Gradient-Free Minimization of Convex Functions , 2015, Foundations of Computational Mathematics.

[9]  Xi Chen,et al.  Evolution Strategies as a Scalable Alternative to Reinforcement Learning , 2017, ArXiv.

[10]  A Stochastic Line Search Method with Convergence Rate Analysis , 2018, 1807.07994.

[11]  Sham M. Kakade,et al.  Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator , 2018, ICML.

[12]  Irina S. Dolinskaya,et al.  A Derivative-Free Trust-Region Algorithm for the Optimization of Functions Smoothed via Gaussian Convolution Using Adaptive Multiple Importance Sampling , 2018, SIAM J. Optim..

[13]  Peter W. Glynn,et al.  On Sampling Rates in Simulation-Based Recursions , 2018, SIAM J. Optim..

[14]  Katya Scheinberg,et al.  Global convergence rate analysis of unconstrained optimization methods based on probabilistic models , 2015, Mathematical Programming.

[15]  Stefan M. Wild,et al.  Derivative-free optimization methods , 2019, Acta Numerica.

[16]  Jorge Nocedal,et al.  Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods , 2018, SIAM J. Optim..

[17]  K. Scheinberg,et al.  A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization , 2019, Foundations of Computational Mathematics.