English
Related papers

Related papers: A parameterized Wasserstein Hamiltonian flow appro…

200 papers

Wasserstein gradient flow (WGF) is a common method to perform optimization over the space of probability measures. While WGF is guaranteed to converge to a first-order stationary point, for nonconvex functionals the converged solution does…

Optimization and Control · Mathematics 2025-09-23 Naoya Yamamoto , Juno Kim , Taiji Suzuki

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

Most inverse problems from physical sciences are formulated as PDE-constrained optimization problems. This involves identifying unknown parameters in equations by optimizing the model to generate PDE solutions that closely match measured…

Optimization and Control · Mathematics 2024-03-12 Qin Li , Li Wang , Yunan Yang

Statistical surrogate modeling of fluid flows is hard because dynamics are multiscale and highly sensitive to initial conditions. Conditional diffusion surrogates can be accurate, but usually need hundreds of stochastic sampling steps. We…

Machine Learning · Computer Science 2026-02-10 Victor Armegioiu , Yannick Ramic , Siddhartha Mishra

This work develops a class of probabilistic algorithms for the numerical solution of nonlinear, time-dependent partial differential equations (PDEs). Current state-of-the-art PDE solvers treat the space- and time-dimensions separately,…

Numerical Analysis · Mathematics 2022-03-10 Nicholas Krämer , Jonathan Schmidt , Philipp Hennig

Deterministic flow models, such as rectified flows, offer a general framework for learning a deterministic transport map between two distributions, realized as the vector field for an ordinary differential equation (ODE). However, they are…

Machine Learning · Computer Science 2024-10-04 Saurabh Singh , Ian Fischer

Sampling from high-dimensional distributions is a fundamental problem in statistical research and practice. However, great challenges emerge when the target density function is unnormalized and contains isolated modes. We tackle this…

Methodology · Statistics 2023-04-11 Yixuan Qiu , Xiao Wang

Mass transport problems arise in many areas of machine learning whereby one wants to compute a map transporting one distribution to another. Generative modeling techniques like Generative Adversarial Networks (GANs) and Denoising Diffusion…

Machine Learning · Computer Science 2024-09-17 Valentin De Bortoli , Iryna Korshunova , Andriy Mnih , Arnaud Doucet

We propose a projected Wasserstein gradient descent method (pWGD) for high-dimensional Bayesian inference problems. The underlying density function of a particle system of WGD is approximated by kernel density estimation (KDE), which faces…

Machine Learning · Computer Science 2021-02-16 Yifei Wang , Peng Chen , Wuchen Li

The dynamical formulation of the optimal transport can be extended through various choices of the underlying geometry (kinetic energy), and the regularization of density paths (potential energy). These combinations yield different…

Machine Learning · Computer Science 2024-07-04 Kirill Neklyudov , Rob Brekelmans , Alexander Tong , Lazar Atanackovic , Qiang Liu , Alireza Makhzani

Score-based diffusion models have emerged as powerful tools in generative modeling, yet their theoretical foundations remain underexplored. In this work, we focus on the Wasserstein convergence analysis of score-based diffusion models.…

Machine Learning · Statistics 2025-02-10 Yifeng Yu , Lu Yu

Minimizing functionals in the space of probability distributions can be done with Wasserstein gradient flows. To solve them numerically, a possible approach is to rely on the Jordan-Kinderlehrer-Otto (JKO) scheme which is analogous to the…

Machine Learning · Computer Science 2022-11-16 Clément Bonet , Nicolas Courty , François Septier , Lucas Drumetz

Sampling from high-dimensional Gibbs measures poses a challenge when the energy landscape consists of multiple metastable states. Enhanced-sampling methods mitigate this difficulty by introducing adaptive biasing potentials to facilitate…

Numerical Analysis · Mathematics 2026-05-06 Liyao Lyu , Siyu Guo , Huan Lei

We study first-order optimality conditions for constrained optimization in the Wasserstein space, whereby one seeks to minimize a real-valued function over the space of probability measures endowed with the Wasserstein distance. Our…

Optimization and Control · Mathematics 2025-03-03 Nicolas Lanzetti , Saverio Bolognani , Florian Dörfler

The semiclassical Schr\"odinger equation with time-dependent potentials is an important model to study electron dynamics under external controls in the mean-field picture. In this paper, we propose two multiscale finite element methods to…

Computational Engineering, Finance, and Science · Computer Science 2019-09-17 Jingrun Chen , Sijing Li , Zhiwen Zhang

We consider the optimization problem of minimizing a functional defined over a family of probability distributions, where the objective functional is assumed to possess a variational form. Such a distributional optimization problem arises…

Machine Learning · Computer Science 2024-04-02 Zhuoran Yang , Yufeng Zhang , Yongxin Chen , Zhaoran Wang

Recent advances in flow-based generative modelling have provided scalable methods for computing the Schr\"odinger Bridge (SB) between distributions, a dynamic form of entropy-regularised Optimal Transport (OT) for the quadratic cost. The…

Machine Learning · Statistics 2025-11-04 Samuel Howard , Peter Potaptchik , George Deligiannidis

By using the theory of analytic vectors and manifolds modelled on normed spaces, we provide a rigorous symplectic differential geometric approach to $t$-dependent Schr\"odinger equations on separable (possibly infinite-dimensional) Hilbert…

Mathematical Physics · Physics 2025-11-18 Javier de Lucas , Julia Lange , Xavier Rivas

We consider the problem of sampling from posterior distributions for Bayesian models where some parameters are restricted to be orthogonal matrices. Such matrices are sometimes used in neural networks models for reasons of regularization…

Machine Learning · Statistics 2019-01-24 Viktor Yanush , Dmitry Kropotov

We show that the Schroedinger equation is a lift of Newton's law of motion on the space of probability measures, where derivatives are taken w.r.t. the Wasserstein Riemannian metric. Here the potential is the sum of the total classical…

Mathematical Physics · Physics 2009-03-12 Max-K. von Renesse
‹ Prev 1 4 5 6 7 8 10 Next ›