Distributed Stochastic Inertial-Accelerated Methods with Delayed Derivatives for Nonconvex Problems
From MaRDI portal
Publication:5863523
DOI10.1137/21M1435719zbMath1487.90508arXiv2107.11513OpenAlexW4280540880MaRDI QIDQ5863523
Yonggui Yan, Jie Chen, Yibo Xu, Yang-yang Xu
Publication date: 1 June 2022
Published in: SIAM Journal on Imaging Sciences (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2107.11513
distributed parallelizationinertial accelerationdelayed (sub)gradientstochastic (sub)gradient method
Numerical mathematical programming methods (65K05) Stochastic programming (90C15) Parallel numerical computation (65Y05) Distributed algorithms (68W15)
Related Items
An extrapolated proximal iteratively reweighted method for nonconvex composite optimization problems
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Accelerated gradient methods for nonconvex nonlinear and stochastic programming
- iPiasco: inertial proximal algorithm for strongly convex optimization
- Local convergence of the heavy-ball method and iPiano for non-convex optimization
- Algorithms of inertial mirror descent in convex problems of stochastic optimization
- On unbounded delays in asynchronous parallel fixed-point algorithms
- Convergence of a splitting inertial proximal method for monotone operators
- Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods
- A hybrid stochastic optimization framework for composite nonconvex optimization
- Efficiency of minimizing compositions of convex functions and smooth maps
- On the convergence of asynchronous parallel iteration with unbounded delays
- Phase retrieval: stability and recovery guarantees
- iPiano: Inertial Proximal Algorithm for Nonconvex Optimization
- Robust principal component analysis?
- Rank-Sparsity Incoherence for Matrix Decomposition
- Robust Stochastic Approximation Approach to Stochastic Programming
- An Incremental Gradient(-Projection) Method with Momentum Term and Adaptive Stepsize Rule
- Stochastic Model-Based Minimization of Weakly Convex Functions
- Weak Convergence of a Relaxed and Inertial Hybrid Projection-Proximal Point Algorithm for Maximal Monotone Operators in Hilbert Space
- Solving (most) of a set of quadratic equalities: composite optimization for robust phase retrieval
- On Distributed Nonconvex Optimization: Projected Subgradient Method for Weakly Convex Problems in Networks
- Proximité et dualité dans un espace hilbertien
- Some methods of speeding up the convergence of iteration methods
- A Stochastic Approximation Method
- The nonsmooth landscape of phase retrieval
- An inertial proximal method for maximal monotone operators via discretization of a nonlinear oscillator with damping
- Heavy-ball method in nonconvex optimization problems