English
Related papers

Related papers: Muon Dynamics as a Spectral Wasserstein Flow

200 papers

We consider the maximum mean discrepancy ($\mathrm{MMD}$) GAN problem and propose a parametric kernelized gradient flow that mimics the min-max game in gradient regularized $\mathrm{MMD}$ GAN. We show that this flow provides a descent…

Machine Learning · Computer Science 2020-11-05 Youssef Mroueh , Truyen Nguyen

This paper proposes a new notion of distributional Input-to-State Stability (dISS) for dynamic systems evolving in probability spaces over a domain. Unlike other norm-based ISS concepts, we rely on the Wasserstein metric, which captures…

Systems and Control · Electrical Eng. & Systems 2026-05-04 Guillem Pascual , Sonia Martínez

The growing adoption of spectrum-aware matrix-valued optimizers such as Muon and Shampoo in deep learning motivates a systematic study of their generalization properties and, in particular, when they might outperform competitive algorithms.…

Machine Learning · Computer Science 2025-12-15 Bhavya Vasudeva , Puneesh Deora , Yize Zhao , Vatsal Sharan , Christos Thrampoulidis

Spectral gradient methods, such as the recently popularized Muon optimizer, are a promising alternative to standard Euclidean gradient descent for training deep neural networks and transformers, but it is still unclear in which regimes they…

Machine Learning · Computer Science 2026-01-15 Damek Davis , Dmitriy Drusvyatskiy

We propose a learning framework for graph kernels, which is theoretically grounded on regularizing optimal transport. This framework provides a novel optimal transport distance metric, namely Regularized Wasserstein (RW) discrepancy, which…

Machine Learning · Computer Science 2021-10-11 Asiri Wijesinghe , Qing Wang , Stephen Gould

We introduce stochastic normalizing flows, an extension of continuous normalizing flows for maximum likelihood estimation and variational inference (VI) using stochastic differential equations (SDEs). Using the theory of rough paths, the…

Machine Learning · Statistics 2020-02-27 Liam Hodgkinson , Chris van der Heide , Fred Roosta , Michael W. Mahoney

Gradient orthogonalization is a simple strategy that shows great utility in speeding up gradient descent. The Muon optimizer (Jordan, Jin, et al., 2024) combines gradient orthogonalization with first-order momentum and achieves significant…

Machine Learning · Computer Science 2025-10-21 Ahmed Khaled , Kaan Ozkara , Tao Yu , Mingyi Hong , Youngsuk Park

The aim of this paper is to provide a mathematical analysis of transformer architectures using a self-attention mechanism with layer normalization. In particular, observed patterns in such architectures resembling either clusters or uniform…

Analysis of PDEs · Mathematics 2025-04-29 Martin Burger , Samira Kabri , Yury Korolev , Tim Roith , Lukas Weigand

To define a steepest descent method over a neural network, we need to choose a norm for each layer, a way to aggregate these norms across layers, and whether to use normalization. We systematically explore different alternatives for…

Machine Learning · Computer Science 2025-10-14 Michael Crawshaw , Chirag Modi , Mingrui Liu , Robert M. Gower

Gromov--Wasserstein (GW) distances compare graphs, shapes, and point clouds through internal distances, without requiring a common coordinate system. This invariance is powerful, but discrete GW is a nonconvex quadratic optimal transport…

Machine Learning · Computer Science 2026-05-15 Ao Xu , Tieru Wu

This paper considers the problem of regression over distributions, which is becoming increasingly important in machine learning. Existing approaches often ignore the geometry of the probability space or are computationally expensive. To…

Machine Learning · Computer Science 2025-10-31 Maksim Maslov , Alexander Kugaevskikh , Matthew Ivanov

Wasserstein gradient flows are continuous time dynamics that define curves of steepest descent to minimize an objective function over the space of probability measures (i.e., the Wasserstein space). This objective is typically a divergence…

Optimization and Control · Mathematics 2021-02-23 Adil Salim , Anna Korba , Giulia Luise

We investigate a Benamou--Brenier type transportation metric for nonnegative measures on a finite reversible Markov chain, which endows the space of measures with a Riemannian structure. Using this geometric framework, we identify a…

Analysis of PDEs · Mathematics 2026-01-21 Qifan Mao , Xinyu Wang , Xiaoping Xue

We propose Sobolev-regularized Maximum Mean Discrepancy (SrMMD) gradient flow, a regularized variant of maximum mean discrepancy (MMD) gradient flow based on a gradient penalty on the witness function. The proposed regularization mitigates…

Machine Learning · Computer Science 2026-05-13 Chenyang Tian , Bharath K. Sriperumbudur , Arthur Gretton , Zonghao Chen

Wasserstein gradient flows provide a powerful means of understanding and solving many diffusion equations. Specifically, Fokker-Planck equations, which model the diffusion of probability measures, can be understood as gradient descent over…

Machine Learning · Computer Science 2021-10-26 Petr Mokrov , Alexander Korotin , Lingxiao Li , Aude Genevay , Justin Solomon , Evgeny Burnaev

We propose a unifying approach that starts from the perturbative construction of trivializing maps by L\"uscher and then improves on it by learning. The resulting continuous normalizing flow model can be implemented using common tools of…

High Energy Physics - Lattice · Physics 2023-03-29 Simone Bacchio , Pan Kessel , Stefan Schaefer , Lorenz Vaitl

The Stein Variational Gradient Descent (SVGD) algorithm is a deterministic particle method for sampling. However, a mean-field analysis reveals that the gradient flow corresponding to the SVGD algorithm (i.e., the Stein Variational Gradient…

Machine Learning · Statistics 2024-05-10 Ye He , Krishnakumar Balasubramanian , Bharath K. Sriperumbudur , Jianfeng Lu

We compute the ground state $u$ of the Gross--Pitaevskii equation (GPE) via Wasserstein gradient descent in diffeomorphism space. We represent the density $\rho=u^2$ as the push-forward of a fixed reference measure through a parameterized…

Numerical Analysis · Mathematics 2026-03-17 Xiangxiong Zhang , Haomin Zhou

Estimating Wasserstein distances between two high-dimensional densities suffers from the curse of dimensionality: one needs an exponential (wrt dimension) number of samples to ensure that the distance between two empirical measures is…

Machine Learning · Statistics 2020-07-13 François-Pierre Paty , Alexandre d'Aspremont , Marco Cuturi

Generative modeling aims to produce new random examples from an unknown target distribution, given access to a finite collection of examples. Among the leading approaches, denoising diffusion probabilistic models (DDPMs) construct such…

Machine Learning · Statistics 2025-06-12 Vahan Arsenyan , Elen Vardanyan , Arnak Dalalyan