A Bregman stochastic method for nonconvex nonsmooth problem beyond global Lipschitz gradient continuity

DOI10.1080/10556788.2023.2189717zbMath1522.90143OpenAlexW4377097065MaRDI QIDQ6078423

Unnamed Author, Deren Han

Publication date: 27 September 2023

Published in: Optimization Methods and Software (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/10556788.2023.2189717

zbMATH Keywords

nonconvexstochastic gradient descentnonsmoothBregman method

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Nonsmooth analysis (49J52) Stochastic programming (90C15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Tensor Decompositions and Applications
• Proximal alternating linearized minimization for nonconvex and nonsmooth problems
• Parseval proximal neural networks
• On the convergence of the proximal algorithm for nonsmooth functions involving analytic features
• A new hybrid generalized proximal point algorithm for variational inequality problems
• Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
• Stochastic proximal gradient methods for nonconvex problems in Hilbert spaces
• A block inertial Bregman proximal algorithm for nonsmooth nonconvex problems with application to symmetric nonnegative matrix tri-factorization
• The developments of proximal point algorithms
• A telescopic Bregmanian proximal gradient method without the global Lipschitz continuity assumption
• On linear convergence of non-Euclidean gradient methods without strong convexity and Lipschitz gradient continuity
• SymNMF: nonnegative low-rank approximation of a similarity matrix for graph clustering
• Forward-backward splitting with Bregman distances
• Sparsity Constrained Nonlinear Optimization: Optimality Conditions and Algorithms
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Variational Analysis
• First Order Methods Beyond Convexity and Lipschitz Gradient Continuity with Applications to Quadratic Inverse Problems
• Trainlets: Dictionary Learning in High Dimensions
• De-noising by soft-thresholding
• Conditional Gradient Algorithmsfor Rank-One Matrix Approximations with a Sparsity Constraint
• A Stochastic Proximal Alternating Minimization for Nonsmooth and Nonconvex Optimization
• Convex-Concave Backtracking for Inertial Bregman Proximal Gradient Algorithms in Nonconvex Optimization
• Robust Low-Rank Matrix Completion via an Alternating Manifold Proximal Gradient Continuation Method
• Novel Proximal Gradient Methods for Nonnegative Matrix Factorization with Sparsity Constraints
• Symmetric Tensors and Symmetric Tensor Rank
• Learning the parts of objects by non-negative matrix factorization
• Universal Regularizers for Robust Sparse Coding and Modeling
• Interior Gradient and Proximal Methods for Convex and Conic Optimization
• A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications
• A Stochastic Approximation Method
• A Bregman Forward-Backward Linesearch Algorithm for Nonconvex Composite Optimization: Superlinear Convergence to Nonisolated Local Minima

This page was built for publication: A Bregman stochastic method for nonconvex nonsmooth problem beyond global Lipschitz gradient continuity