English
Related papers

Related papers: On the Convergence of Wasserstein Gradient Descent…

200 papers

Generative adversarial nets (GANs) and variational auto-encoders have significantly improved our distribution modeling capabilities, showing promise for dataset augmentation, image-to-image translation and feature learning. However, to…

We present a novel approach to approximate Gaussian and mixture-of-Gaussians filtering. Our method relies on a variational approximation via a gradient-flow representation. The gradient flow is derived from a Kullback--Leibler discrepancy…

Computation · Statistics 2023-06-21 Adrien Corenflos , Hany Abdulsamad

Wasserstein distances are increasingly used in a wide variety of applications in machine learning. Sliced Wasserstein distances form an important subclass which may be estimated efficiently through one-dimensional sorting operations. In…

Machine Learning · Statistics 2019-04-08 Mark Rowland , Jiri Hron , Yunhao Tang , Krzysztof Choromanski , Tamas Sarlos , Adrian Weller

We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. Our method iteratively transports a set of particles to match the target distribution, by applying a form of…

Machine Learning · Statistics 2019-09-10 Qiang Liu , Dilin Wang

We provide non asymptotic rates of convergence of the Wasserstein Generative Adversarial networks (WGAN) estimator. We build neural networks classes representing the generators and discriminators which yield a GAN that achieves the minimax…

Statistics Theory · Mathematics 2025-03-13 Arthur Stéphanovitch , Eddie Aamari , Clément Levrard

Ensembles of deep neural networks have achieved great success recently, but they do not offer a proper Bayesian justification. Moreover, while they allow for averaging of predictions over several hypotheses, they do not provide any…

Machine Learning · Computer Science 2021-06-23 Francesco D'Angelo , Vincent Fortuin , Florian Wenzel

Distribution matching is central to many vision and graphics tasks, where the widely used Wasserstein distance is too costly to compute for high dimensional distributions. The Sliced Wasserstein Distance (SWD) offers a scalable alternative,…

Graphics · Computer Science 2025-10-02 Mark Boss , Andreas Engelhardt , Simon Donné , Varun Jampani

While classical forms of stochastic gradient descent algorithm treat the different coordinates in the same way, a framework allowing for adaptive (non uniform) coordinate sampling is developed to leverage structure in data. In a non-convex…

Machine Learning · Statistics 2022-10-18 Rémi Leluc , François Portier

The smooth 1-Wasserstein distance (SWD) $W_1^\sigma$ was recently proposed as a means to mitigate the curse of dimensionality in empirical approximation while preserving the Wasserstein structure. Indeed, SWD exhibits parametric convergence…

Statistics Theory · Mathematics 2022-02-28 Ritwik Sadhu , Ziv Goldfeld , Kengo Kato

Score-based generative models are shown to achieve remarkable empirical performances in various applications such as image generation and audio synthesis. However, a theoretical understanding of score-based diffusion models is still…

Machine Learning · Computer Science 2022-12-14 Dohyun Kwon , Ying Fan , Kangwook Lee

Consider an empirical measure $\mathbb{P}_n$ induced by $n$ iid samples from a $d$-dimensional $K$-subgaussian distribution $\mathbb{P}$ and let $\gamma = N(0,\sigma^2 I_d)$ be the isotropic Gaussian measure. We study the speed of…

Probability · Mathematics 2025-02-11 Adam Block , Zeyu Jia , Yury Polyanskiy , Alexander Rakhlin

This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparameterized two-layer neural networks. In particular, we consider the minimax optimization problem stemming from estimating linear…

Machine Learning · Computer Science 2024-10-25 Yuchen Zhu , Yufeng Zhang , Zhaoran Wang , Zhuoran Yang , Xiaohong Chen

Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference. In this work, we enhance SVGD by leveraging preconditioning matrices, such as the…

Machine Learning · Statistics 2019-11-06 Dilin Wang , Ziyang Tang , Chandrajit Bajaj , Qiang Liu

The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by…

Optimization and Control · Mathematics 2025-11-21 Fabio Nobile , Matteo Raviola , Nathan Schaeffer

This paper studies iterative schemes for measure transfer and approximation problems, which are defined through a slicing-and-matching procedure. Similar to the sliced Wasserstein distance, these schemes benefit from the availability of…

Numerical Analysis · Mathematics 2026-03-17 Shiying Li , Caroline Moosmueller , Yongzhe Wang

We present a stochastic descent algorithm for unconstrained optimization that is particularly efficient when the objective function is slow to evaluate and gradients are not easily obtained, as in some PDE-constrained optimization and…

Optimization and Control · Mathematics 2024-07-08 David Kozak , Stephen Becker , Alireza Doostan , Luis Tenorio

The training and test data for deep-neural-network-based classifiers are usually assumed to be sampled from the same distribution. When part of the test samples are drawn from a distribution that is sufficiently far away from that of the…

Machine Learning · Computer Science 2021-12-14 Yinan Wang , Wenbo Sun , Jionghua "Judy" Jin , Zhenyu "James" Kong , Xiaowei Yue

We introduce a novel framework for graph signal processing (GSP) that models signals as graph distribution-valued signals (GDSs), which are probability distributions in the Wasserstein space. This approach overcomes key limitations of…

Machine Learning · Statistics 2026-03-25 Yanan Zhao , Feng Ji , Xingchao Jian , Wee Peng Tay

In object detection, a well-defined similarity metric can significantly enhance model performance. Currently, the IoU-based similarity metric is the most commonly preferred choice for detectors. However, detectors using IoU as a similarity…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Ziqian Guan , Xieyi Fu , Pengjun Huang , Hengyuan Zhang , Hubin Du , Yongtao Liu , Yinglin Wang , Qang Ma

Stochastic gradient descent (SGD) has been a go-to algorithm for nonconvex stochastic optimization problems arising in machine learning. Its theory however often requires a strong framework to guarantee convergence properties. We hereby…

Optimization and Control · Mathematics 2025-03-11 Azar Louzi