Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization

• URL: http://arxiv.org/abs/2606.27767v1
• Date: Fri, 26 Jun 2026 06:53:03 GMT
• Title: Difference of Convex Programming in the Wasserstein Space with Applications to MMD Optimization
• Abstract summary: This paper presents a class of objectives over the Wasserstein space.<n>Under convex assumptions, we prove almost station along the gradient of DC decompositions.<n>Our main is on the Maximum Discreprepancy (MMD) and the Energy (ED) scheme.
• Score: 13.544454495712037
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optimizing functionals over the space of probability measures is now ubiquitous in machine learning. A widely used approach is to perform the optimization directly over the Wasserstein space, but many objective functionals of practical interest are non-convex along Wasserstein geodesics, making the analysis of standard first-order methods challenging. In this work, we study a class of objectives over the Wasserstein space that admit a difference-of-convex (DC) decomposition and we lift the classical convex-concave procedure (CCCP) to this setting. Under smoothness and strong convexity assumptions on the convex components of the decomposition, we prove almost stationarity along the iterates of the resulting algorithm. Our main focus is on the Maximum Mean Discrepancy (MMD) and the Energy Distance (ED) functionals, for which we develop explicit Wasserstein DC decompositions, and establish local convergence of the scheme under mild assumptions. Empirically, we show that well-chosen DC decompositions yield faster and more stable convergence than Wasserstein gradient descent on these MMD objectives.

Related papers

• Random Coordinate Descent on the Wasserstein Space of Probability Measures [1.5888343554854376]
  Optimization over the space of probability measures endowed with the Wasserstein-2 geometry is central to modern machine learning and mean-field modeling.<n>We propose a coordinate descent framework specifically for the Wasserstein manifold, introducing both Random Wasserstein Coordinate Descent (RWCD) and Random Wasserstein Coordinate Descent (RWCP)<n> Numerical experiments on ill-conditioned energies demonstrate that our framework offers significant speedups over conventional full-gradient methods.
  arXiv  Detail & Related papers  (2026-04-02T04:36:56Z)
• Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points [54.06226763868876]
  Wasserstein flow (WGF) is a common method to perform optimization over the space of measures.<n>We show that PWGF converges to a global optimum in terms of general non objectives.
  arXiv  Detail & Related papers  (2025-09-21T08:14:20Z)
• Wasserstein Distributionally Robust Regret Optimization [0.0]
  We provide a systematic analysis of Wasserstein DRRO, paralleling known results for Wasserstein DRO.<n>Under smoothness and regularity conditions, we show that Wasserstein DRRO coincides with Empirical Risk Minimization (ERM) up to first-order terms.<n>We show that the regret can be computed by maximizing two one-dimensional concave functions.
  arXiv  Detail & Related papers  (2025-04-15T01:47:11Z)
• Enhancing Distributional Robustness in Principal Component Analysis by Wasserstein Distances [7.695578200868269]
  We consider the distributionally robust optimization (DRO) model of principal component analysis (PCA) to account for uncertainty in the underlying probability distribution.<n>The resulting formulation leads to a nonsmooth constrained min-max optimization problem, where the ambiguity set captures the distributional uncertainty by the type-$2$ Wasserstein distance.<n>This explicit characterization equivalently reformulates the original DRO model into a minimization problem on the Stiefel manifold with intricate nonsmooth terms.
  arXiv  Detail & Related papers  (2025-03-04T11:00:08Z)
• Continuous-time Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space [21.12668895845275]
  We extend the family of continuous optimization methods in the Wasserstein space by extending the gradient on flow into the gradient descent.<n>By leveraging the property of Wasserstein space, we construct differential equations (SDEs) to approximate the corresponding discrete Euclidean dynamics.<n>Finally, we establish convergence rates of the proposed flows, which align with those known in the Euclidean setting.
  arXiv  Detail & Related papers  (2024-01-24T15:35:44Z)
• Mean-Square Analysis with An Application to Optimal Dimension Dependence of Langevin Monte Carlo [60.785586069299356]
  This work provides a general framework for the non-asymotic analysis of sampling error in 2-Wasserstein distance. Our theoretical analysis is further validated by numerical experiments.
  arXiv  Detail & Related papers  (2021-09-08T18:00:05Z)
• Large-Scale Wasserstein Gradient Flows [84.73670288608025]
  We introduce a scalable scheme to approximate Wasserstein gradient flows. Our approach relies on input neural networks (ICNNs) to discretize the JKO steps. As a result, we can sample from the measure at each step of the gradient diffusion and compute its density.
  arXiv  Detail & Related papers  (2021-06-01T19:21:48Z)
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework [100.36569795440889]
  This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information. We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
  arXiv  Detail & Related papers  (2020-12-21T17:29:58Z)
• Projection Robust Wasserstein Distance and Riemannian Optimization [107.93250306339694]
  We show that projection robustly solidstein (PRW) is a robust variant of Wasserstein projection (WPP) This paper provides a first step into the computation of the PRW distance and provides the links between their theory and experiments on and real data.
  arXiv  Detail & Related papers  (2020-06-12T20:40:22Z)
• The Wasserstein Proximal Gradient Algorithm [23.143814848127295]
  Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures. We propose a Forward Backward (FB) discretization scheme that can tackle the case where the objective function is the sum of a smooth and a nonsmooth geodesically convex terms.
  arXiv  Detail & Related papers  (2020-02-07T22:19:32Z)
• A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models [93.24030378630175]
  We propose a novel numerical scheme to optimize the gradient flows for learning energy-based models (EBMs) We derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation. Compared with existing schemes, Wasserstein gradient flow is a smoother and near-optimal numerical scheme to approximate real data densities.
  arXiv  Detail & Related papers  (2019-10-31T02:26:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.