Stochastic saddle-point optimization for the Wasserstein barycenter problem

DOI10.1007/S11590-021-01834-WzbMath1497.90139arXiv2006.06763OpenAlexW4210382974MaRDI QIDQ2162697

Daniil Tiapkin, Alexander V. Gasnikov, Pavel Dvurechensky

Publication date: 9 August 2022

Published in: Optimization Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2006.06763

zbMATH Keywords

stochastic optimizationcomputational optimal transportsaddle-point optimizationWasserstein barycenter problem

Mathematics Subject Classification ID

Stochastic programming (90C15) Complementarity and equilibrium problems and variational inequalities (finite dimensions) (aspects of mathematical programming) (90C33)

Related Items (2)

Generalized mirror prox algorithm for monotone variational inequalities: Universality and inexact oracle ⋮ Sion’s Minimax Theorem in Geodesic Metric Spaces and a Riemannian Extragradient Algorithm

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Computational Optimal Transport: With Applications to Data Science
• Dual approaches to the minimization of strongly convex functionals with a simple structure under affine constraints
• Generalized mirror prox algorithm for monotone variational inequalities: Universality and inexact oracle
• Gradient methods for problems with inexact model of the objective
• Alternating minimization methods for strongly convex optimization
• Statistical inference for Bures-Wasserstein barycenters
• Accelerated primal-dual gradient descent with linesearch for convex, nonconvex, and nonsmooth optimization problems
• Distribution's template estimate with Wasserstein metrics
• Mirror descent and convex optimization problems with non-smooth inequality constraints
• A stable alternative to Sinkhorn's algorithm for regularized optimal transport
• Fast Primal-Dual Gradient Method for Strongly Convex Minimization Problems with Linear Constraints
• Barycenters in the Wasserstein Space
• A Wasserstein-Type Distance in the Space of Gaussian Mixture Models
• Support Vector Machines
• Robust Stochastic Approximation Approach to Stochastic Programming
• Variational Analysis
• Randomized Wasserstein Barycenter Computation: Resampling with Statistical Guarantees
• Primal–dual accelerated gradient methods with small-dimensional relaxation oracle
• An Optimal Algorithm for Decentralized Finite-Sum Optimization
• Stabilized Sparse Scaling Algorithms for Entropy Regularized Transport Problems
• Iterative Bregman Projections for Regularized Transportation Problems
• Inexact model: a framework for optimization and variational inequalities
• Real and functional analysis
• Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory

This page was built for publication: Stochastic saddle-point optimization for the Wasserstein barycenter problem