English
Related papers

Related papers: Implicit Bias of the JKO Scheme

200 papers

We present a computationally efficient framework, called $\texttt{FlowDRO}$, for solving flow-based distributionally robust optimization (DRO) problems with Wasserstein uncertainty sets while aiming to find continuous worst-case…

Machine Learning · Computer Science 2024-02-27 Chen Xu , Jonghyeok Lee , Xiuyuan Cheng , Yao Xie

We study a natural Wasserstein gradient flow on manifolds of probability distributions with discrete sample spaces. We derive the Riemannian structure for the probability simplex from the dynamical formulation of the Wasserstein distance on…

Optimization and Control · Mathematics 2021-04-19 Wuchen Li , Guido Montufar

Transfer learning is a popular strategy to leverage external knowledge and improve statistical efficiency, particularly with a limited target sample. We propose a novel knowledge-guided Wasserstein Distributionally Robust Optimization…

Machine Learning · Computer Science 2025-02-13 Zitao Wang , Ziyuan Wang , Molei Liu , Nian Si

We prove the equivalence between the notion of Wasserstein gradient flow for a one-dimensional nonlocal transport PDE with attractive/repulsive Newtonian potential on one side, and the notion of entropy solution of a Burgers-type scalar…

Analysis of PDEs · Mathematics 2013-10-16 Giovanni A. Bonaschi , José A. Carrillo , Marco Di Francesco , Mark A. Peletier

Applications of optimal transport have recently gained remarkable attention thanks to the computational advantages of entropic regularization. However, in most situations the Sinkhorn approximation of the Wasserstein distance is replaced by…

Machine Learning · Statistics 2019-06-04 Giulia Luise , Alessandro Rudi , Massimiliano Pontil , Carlo Ciliberto

We propose and analyze numerical schemes for the gradient flow of $Q$-tensor with the quasi-entropy. The quasi-entropy is a strictly convex, rotationally invariant elementary function, giving a singular potential constraining the…

Numerical Analysis · Mathematics 2021-10-22 Yanli Wang , Jie Xu

This is the first of a series of papers devoted to a thorough analysis of the class of gradient flows in a metric space $(X,\mathsf{d})$ that can be characterized by Evolution Variational Inequalities. We present new results concerning the…

Functional Analysis · Mathematics 2018-10-10 Matteo Muratori , Giuseppe Savaré

As the problem of minimizing functionals on the Wasserstein space encompasses many applications in machine learning, different optimization algorithms on $\mathbb{R}^d$ have received their counterpart analog on the Wasserstein space. We…

Optimization and Control · Mathematics 2024-11-20 Clément Bonet , Théo Uscidda , Adam David , Pierre-Cyril Aubin-Frankowski , Anna Korba

We introduce a class of high order accurate, semi-implicit Runge-Kutta schemes in the general setting of evolution equations that arise as gradient flow for a cost function, possibly with respect to an inner product that depends on the…

Numerical Analysis · Mathematics 2021-10-04 Alexander Zaitzeff , Selim Esedoglu , Krishna Garikipati

The purpose of this paper is to answer a few open questions in the interface of kernel methods and PDE gradient flows. Motivated by recent advances in machine learning, particularly in generative modeling and sampling, we present a rigorous…

Machine Learning · Statistics 2024-10-29 Jia-Jie Zhu , Alexander Mielke

This paper develops a generative model by minimizing the second-order Wasserstein loss (the $W_2$ loss) through a distribution-dependent ordinary differential equation (ODE), whose dynamics involves the Kantorovich potential associated with…

Machine Learning · Statistics 2026-05-14 Yu-Jui Huang , Zachariah Malik

The $E$-optimality criterion for a regression model maximizes the smallest eigenvalue of the information matrix and becomes non-differentiable when this eigenvalue has multiplicity greater than one. Working in the $2$-Wasserstein space, we…

Optimization and Control · Mathematics 2026-04-17 Jieling Shi , Kim-Chuan Toh , Xin T. Tong , Weng Kee Wong

We introduce a novel variant of the JKO scheme to approximate Darcy's law with a pressure dependent source term. By introducing a new variable that implicitly controls the source term, our scheme is still able to use the standard…

Analysis of PDEs · Mathematics 2020-12-30 Matt Jacobs , Inwon Kim , Jiajun Tong

The dynamics of probability density functions have been extensively studied in computational science and engineering to understand physical phenomena and facilitate algorithmic design. Of particular interest are dynamics formulated as…

Analysis of PDEs · Mathematics 2026-03-16 José A. Carrillo , Yifan Chen , Daniel Zhengyu Huang , Jiaoyang Huang , Dongyi Wei

Learning algorithms for implicit generative models can optimize a variety of criteria that measure how the data distribution differs from the implicit model distribution, including the Wasserstein distance, the Energy distance, and the…

Machine Learning · Statistics 2019-08-23 Leon Bottou , Martin Arjovsky , David Lopez-Paz , Maxime Oquab

We consider a class of time-homogeneous diffusion processes on $\mathbb{R}^{n}$ with common invariant measure but varying volatility matrices. In Euclidean space, we show via stochastic control of the diffusion coefficient that the…

Probability · Mathematics 2023-10-31 Bertram Tschiderer

This paper is devoted to existence and uniqueness results for classes of nonlinear diffusion equations (or systems) which may be viewed as regular perturbations of Wasserstein gradient flows. First, in the case. where the drift is a…

Analysis of PDEs · Mathematics 2015-05-07 Guillaume Carlier , Maxime Laborde

Policy gradients methods often achieve better performance when the change in policy is limited to a small Kullback-Leibler divergence. We derive policy gradients where the change in policy is limited to a small Wasserstein distance (or…

Machine Learning · Computer Science 2017-12-21 Pierre H. Richemond , Brendan Maginnis

We propose a mathematically principled PDE gradient flow framework for distributionally robust optimization (DRO). Exploiting the recent advances in the intersection of Markov Chain Monte Carlo sampling and gradient flow theory, we show…

Optimization and Control · Mathematics 2026-05-27 Zusen Xu , Jia-Jie Zhu

In this paper, we present a novel second-order generalised rotational discrete gradient scheme for numerically approximating the orthonormal frame gradient flow of biaxial nematic liquid crystals. This scheme relies on reformulating the…

Numerical Analysis · Mathematics 2023-10-17 Hanbin Wang , Jie Xu , Zhiguo Yang
‹ Prev 1 3 4 5 6 7 10 Next ›