Stochastic Model-Based Minimization of Weakly Convex Functions

DOI10.1137/18M1178244zbMath1415.65136arXiv1803.06523OpenAlexW2963190258WikidataQ128585540 ScholiaQ128585540MaRDI QIDQ4620418

Damek Davis, Dmitriy Drusvyatskiy

Publication date: 8 February 2019

Published in: SIAM Journal on Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1803.06523

zbMATH Keywords

subgradient stochastic proximal Moreau envelope weakly convex prox-linear

Mathematics Subject Classification ID

Numerical mathematical programming methods (65K05) Convex programming (90C25) Nonlinear programming (90C30) Stochastic programming (90C15)

Related Items

Complexity of an inexact proximal-point penalty method for constrained smooth non-convex optimization, Weakly-convex–concave min–max optimization: provable algorithms and applications in machine learning, Proximal methods avoid active strict saddles of weakly convex functions, Moreau envelope augmented Lagrangian method for nonconvex optimization with linear constraints, A stochastic extra-step quasi-Newton method for nonsmooth nonconvex optimization, Zeroth-Order Stochastic Compositional Algorithms for Risk-Aware Learning, A stochastic subgradient method for distributionally robust non-convex and non-smooth learning, Stochastic Multilevel Composition Optimization Algorithms with Level-Independent Convergence Rates, Sub-linear convergence of a stochastic proximal iteration method in Hilbert space, Graphical Convergence of Subgradients in Nonconvex Optimization and Learning, Sublinear Convergence of a Tamed Stochastic Gradient Descent Method in Hilbert Space, Escaping Strict Saddle Points of the Moreau Envelope in Nonsmooth Optimization, Hybrid SGD algorithms to solve stochastic composite optimization problems with application in sparse portfolio selection problems, A dual-based stochastic inexact algorithm for a class of stochastic nonsmooth convex composite problems, Nonconvex optimization with inertial proximal stochastic variance reduction gradient, A Zeroth-Order Proximal Stochastic Gradient Method for Weakly Convex Stochastic Optimization, Momentum-based variance-reduced proximal stochastic gradient method for composite nonconvex stochastic optimization, Learning with risks based on M-location, Conditions for linear convergence of the gradient method for non-convex optimization, Stochastic AUC optimization with general loss, The landscape of the proximal point method for nonconvex-nonconcave minimax optimization, Branch-and-bound performance estimation programming: a unified methodology for constructing optimal optimization methods, Unnamed Item, Radial duality. II: Applications and algorithms, Worst-case complexity of an SQP method for nonlinear equality constrained stochastic optimization, On Proximal Algorithms with Inertial Effects Beyond Monotonicity, Optimal Convergence Rates for the Proximal Bundle Method, Consistent approximations in composite optimization, Alternating Proximal-Gradient Steps for (Stochastic) Nonconvex-Concave Minimax Problems, MultiComposite Nonconvex Optimization for Training Deep Neural Networks, Algorithms with gradient clipping for stochastic optimization with heavy-tailed noise, On the computation of equilibria in monotone and potential stochastic hierarchical games, Stochastic Model-Based Minimization of Weakly Convex Functions, Primal-dual block-proximal splitting for a class of non-convex problems, Recent Theoretical Advances in Non-Convex Optimization, Nonsmooth optimization using Taylor-like models: error bounds, convergence, and termination criteria, Convergence of a stochastic subgradient method with averaging for nonsmooth nonconvex constrained optimization, Unnamed Item, An Accelerated Inexact Proximal Point Method for Solving Nonconvex-Concave Min-Max Problems, An algorithm for the minimization of nonsmooth nonconvex functions using inexact evaluations and its worst-case complexity, Variable smoothing for weakly convex composite functions, Stochastic subgradient method converges on tame functions, Variable smoothing incremental aggregated gradient method for nonsmooth nonconvex regularized optimization, Stochastic proximal splitting algorithm for composite minimization, A Single Timescale Stochastic Approximation Method for Nested Stochastic Optimization, A zeroth order method for stochastic weakly convex optimization, Stochastic generalized gradient methods for training nonconvex nonsmooth neural networks, Proximally Guided Stochastic Subgradient Method for Nonsmooth, Nonconvex Problems, Low-rank matrix recovery with composite optimization: good conditioning and rapid convergence, Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity, Accelerate stochastic subgradient method by leveraging local growth condition, A Stochastic Subgradient Method for Nonsmooth Nonconvex Multilevel Composition Optimization, Stochastic relaxed inertial forward-backward-forward splitting for monotone inclusions in Hilbert spaces, Ghost Penalties in Nonconvex Constrained Optimization: Diminishing Stepsizes and Iteration Complexity, Weakly Convex Optimization over Stiefel Manifold Using Riemannian Subgradient-Type Methods, Stochastic variance-reduced prox-linear algorithms for nonconvex composite optimization, Perturbed iterate SGD for Lipschitz continuous loss functions, Distributed stochastic nonsmooth nonconvex optimization, Distributed Stochastic Inertial-Accelerated Methods with Delayed Derivatives for Nonconvex Problems, Provably training overparameterized neural network classifiers with non-convex constraints, Stochastic Difference-of-Convex-Functions Algorithms for Nonconvex Programming, A Study of Convex Convex-Composite Functions via Infimal Convolution with Applications

Uses Software

Cites Work