paper-with-me

Papers

(De)-regularized Maximum Mean Discrepancy Gradient Flow

2024-09-23 · Zonghao Chen, Aratrika Mustafi, Pierre Glaser, Anna Korba, Arthur Gretton, Bharath K. Sriperumbudur

We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distribution to target distribution with only target samples, either lack tractable numerical implementation ($f$-divergence flows) or require strong assumptions, and modifications such as noise injection, to ensure convergence (Maximum Mean Discrepancy flows). In contrast, DrMMD flow can simultaneously (i) guarantee near-global convergence for a broad class of targets in both continuous and discrete time, and (ii) be implemented in closed form using only samples. The former is achieved by leveraging the connection between the DrMMD and the $\chi^2$-divergence, while the latter comes by treating DrMMD as MMD with a de-regularized kernel. Our numerical scheme uses an adaptive de-regularization schedule throughout the flow to optimally trade off between discretization errors and deviations from the $\chi^2$ regime. The potential application of the DrMMD flow is demonstrated across several numerical experiments, including a large-scale setting of training student/teacher networks.

📄 PDF Abstract BibTeX arXiv:2409.14980

Code (1)

hudsonchen/drmmd 공식 구현 jax

Similar Papers 제목 키워드 기반

Sobolev Regularized MMD Gradient Flow

2026-05-12 · Chenyang Tian, Bharath K. Sriperumbudur, Arthur Gretton, Zonghao Chen arxiv

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 regul…

Wasserstein Gradient Flows for Moreau Envelopes of f-Divergences in Reproducing Kernel Hilbert Spaces

2024-02-07 · Viktor Stein, Sebastian Neumayer, Nicolaj Rux, Gabriele Steidl

Commonly used $f$-divergences of measures, e.g., the Kullback-Leibler divergence, are subject to limitations regarding the support of the involved measures. A remedy is regularizing the $f$-divergence by a squared maximu…

On the Convergence of Gradient Descent in GANs: MMD GAN As a Gradient Flow

2020-11-04 · Youssef Mroueh, Truyen Nguyen

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 prov…

Maximum Mean Discrepancy Gradient Flow

2019-06-11 · NeurIPS 2019 12 · Michael Arbel, Anna Korba, Adil Salim, Arthur Gretton

We construct a Wasserstein gradient flow of the maximum mean discrepancy (MMD) and study its convergence properties. The MMD is an integral probability metric defined for a reproducing kernel Hilbert space (RKHS), and se…

KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support

2021-06-16 · NeurIPS 2021 12 · Pierre Glaser, Michael Arbel, Arthur Gretton

We study the gradient flow for a relaxed approximation to the Kullback-Leibler (KL) divergence between a moving source and a fixed target distribution. This approximation, termed the KALE (KL approximate lower-bound esti…