Global Convergence Rate Analysis of a Generic Line Search Algorithm with Noise
From MaRDI portal
Publication:4997171
DOI10.1137/19M1291832zbMath1470.90129arXiv1910.04055MaRDI QIDQ4997171
Katya Scheinberg, Liyuan Cao, Albert S. Berahas
Publication date: 28 June 2021
Published in: SIAM Journal on Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1910.04055
Related Items
Full-low evaluation methods for derivative-free optimization, Zeroth-Order Regularized Optimization (ZORO): Approximately Sparse Gradients and Adaptive Sampling, Zeroth-order methods for noisy Hölder-gradient functions, Stochastic Trust-Region Methods with Trust-Region Radius Depending on Probabilistic Models, Inequality constrained stochastic nonlinear optimization via active-set sequential quadratic programming, A trust region method for noisy unconstrained optimization, Convergence Properties of an Objective-Function-Free Optimization Regularization Algorithm, Including an \(\boldsymbol{\mathcal{O}(\epsilon^{-3/2})}\) Complexity Bound, A line search based proximal stochastic gradient algorithm with dynamical variance reduction, Trust-region algorithms: probabilistic complexity and intrinsic noise with applications to subsampling techniques, Unifying framework for accelerated randomized methods in convex optimization, The impact of noise on evaluation complexity: the deterministic trust-region case, Recent Theoretical Advances in Non-Convex Optimization, Adaptive regularization for nonconvex optimization using inexact function values and randomly perturbed derivatives, Expected complexity analysis of stochastic direct-search, A stochastic first-order trust-region method with inexact restoration for finite-sum minimization, A Noise-Tolerant Quasi-Newton Algorithm for Unconstrained Optimization, LSOS: Line-search second-order stochastic optimization methods for nonconvex finite sums
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Sample size selection in optimization methods for machine learning
- Introductory lectures on convex optimization. A basic course.
- Global convergence rate analysis of unconstrained optimization methods based on probabilistic models
- Random gradient-free minimization of convex functions
- Estimating Computational Noise
- Implicit Filtering
- Introduction to Derivative-Free Optimization
- On Sampling Rates in Simulation-Based Recursions
- Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods
- A Derivative-Free Trust-Region Algorithm for the Optimization of Functions Smoothed via Gaussian Convolution Using Adaptive Multiple Importance Sampling
- Benchmarking Derivative-Free Optimization Algorithms
- On the Global Convergence of Trust Region Algorithms Using Inexact Gradient Information
- A Stochastic Line Search Method with Expected Complexity Analysis
- Derivative-free optimization methods
