Universal method for stochastic composite optimization problems
From MaRDI portal
Publication:1746349
DOI10.1134/S0965542518010050zbMath1457.90099OpenAlexW2790570656MaRDI QIDQ1746349
Yu. E. Nesterov, Alexander V. Gasnikov
Publication date: 25 April 2018
Published in: Computational Mathematics and Mathematical Physics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1134/s0965542518010050
stochastic optimizationfast gradient methodcomposite optimizationuniversal methodmethod of similar trianglesstrongly convex case
Related Items
Efficient numerical methods to solve sparse linear equations with application to PageRank, Generalized mirror prox algorithm for monotone variational inequalities: Universality and inexact oracle, Comparative analysis of gradient methods for source identification in a diffusion-logistic model, Dual approaches to the minimization of strongly convex functionals with a simple structure under affine constraints, An optimal gradient method for smooth strongly convex minimization, Gradient-free methods for non-smooth convex stochastic optimization with heavy-tailed noise on convex compact, Numerical algorithm for source determination in a diffusion-logistic model from integral data based on tensor optimization, Accelerated gradient methods with absolute and relative noise in the gradient, Hyperfast second-order local solvers for efficient statistically preconditioned distributed optimization, Multistage transportation model and sufficient conditions for its potentiality, First-order methods for convex optimization, Unifying framework for accelerated randomized methods in convex optimization, Algorithms with gradient clipping for stochastic optimization with heavy-tailed noise, Recent theoretical advances in decentralized distributed convex optimization, Contracting Proximal Methods for Smooth Convex Optimization, Dual methods for finding equilibriums in mixed models of flow distribution in large transportation networks, Accelerated directional search with non-Euclidean prox-structure, Decentralized and parallel primal and dual accelerated methods for stochastic convex programming problems, Universal method of searching for equilibria and stochastic equilibria in transportation networks, Generalized Momentum-Based Methods: A Hamiltonian Perspective, Noisy zeroth-order optimization for non-smooth saddle point problems, Inexact model: a framework for optimization and variational inequalities, Convex optimization with inexact gradients in Hilbert space and applications to elliptic inverse problems, Machine learning algorithms of relaxation subgradient method with space extension
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Primal-dual subgradient methods for convex problems
- Smooth minimization of non-smooth functions
- Efficient numerical methods for entropy-linear programming problems
- Gradient methods for minimizing composite functions
- First-order methods of smooth convex optimization with inexact oracle
- On lower complexity bounds for large-scale smooth convex optimization
- Universal gradient methods for convex optimization problems
- Stochastic intermediate gradient method for convex problems with stochastic inexact oracle
- Dual approaches to the minimization of strongly convex functionals with a simple structure under affine constraints
- Adaptive restart for accelerated gradient schemes
- Stochastic intermediate gradient method for convex optimization problems
- Lectures on Modern Convex Optimization
- Deterministic and stochastic primal-dual subgradient algorithms for uniformly convex minimization
