English
Related papers

Related papers: Generative Sliced MMD Flows with Riesz Kernels

200 papers

Generative artificial intelligence (AI) has made unprecedented advances in vision language models over the past two years. During the generative process, new samples (images) are generated from an unknown high-dimensional distribution.…

Graphics · Computer Science 2025-10-13 Gurprit Singh , Wenzel Jakob

We present multiplexed gradient descent (MGD), a gradient descent framework designed to easily train analog or digital neural networks in hardware. MGD utilizes zero-order optimization techniques for online training of hardware neural…

Machine Learning · Computer Science 2023-08-17 Adam N. McCaughan , Bakhrom G. Oripov , Natesh Ganesh , Sae Woo Nam , Andrew Dienstfrey , Sonia M. Buckley

Restricted Boltzmann machines (RBMs) are a powerful class of generative models, but their training requires computing a gradient that, unlike supervised backpropagation on typical loss functions, is notoriously difficult even to…

Machine Learning · Computer Science 2020-11-03 Haik Manukian , Yan Ru Pei , Sean R. B. Bearden , Massimiliano Di Ventra

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

Mirror Descent (MD) is a scalable first-order method widely used in large-scale optimization, with applications in image processing, policy optimization, and neural network training. This paper generalizes MD to optimization on Riemannian…

Machine Learning · Statistics 2026-03-19 Jiaxin Jiang , Lei Shi , Jiyuan Tan

We present an algorithm for producing discrete distributions with a prescribed nearest-neighbor distance function. Our approach is a combination of quasi-Monte Carlo (Q-MC) methods and weighted Riesz energy minimization: the initial…

Numerical Analysis · Mathematics 2018-08-13 O. Vlasiuk , T. Michaels , N. Flyer , B. Fornberg

We propose a method to optimize the representation and distinguishability of samples from two probability distributions, by maximizing the estimated power of a statistical test based on the maximum mean discrepancy (MMD). This optimized MMD…

Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances between probability distributions that have attracted abundant…

Machine Learning · Statistics 2023-06-01 Titouan Vayer , Rémi Gribonval

Gaussian mixture models (GMM) are powerful parametric tools with many applications in machine learning and computer vision. Expectation maximization (EM) is the most popular algorithm for estimating the GMM parameters. However, EM…

Computer Vision and Pattern Recognition · Computer Science 2017-11-17 Soheil Kolouri , Gustavo K. Rohde , Heiko Hoffmann

Recently used in various machine learning contexts, the Gromov-Wasserstein distance (GW) allows for comparing distributions whose supports do not necessarily lie in the same metric space. However, this Optimal Transport (OT) distance…

Machine Learning · Statistics 2022-10-21 Titouan Vayer , Rémi Flamary , Romain Tavenard , Laetitia Chapel , Nicolas Courty

We analyse the performance of several iterative algorithms for the quantisation of a probability measure $\mu$, based on the minimisation of a Maximum Mean Discrepancy (MMD). Our analysis includes kernel herding, greedy MMD minimisation and…

Machine Learning · Statistics 2022-04-29 Luc Pronzato

Pairwise distance-based costs are crucial for self-supervised and contrastive feature learning. Mixture Density Networks (MDNs) are a widely used approach for generative models and density approximation, using neural networks to produce…

Machine Learning · Computer Science 2025-10-09 Bo Hu , José C. Príncipe

This paper provides results on Wasserstein gradient flows between measures on the real line. Utilizing the isometric embedding of the Wasserstein space $\mathcal P_2(\mathbb R)$ into the Hilbert space $L_2((0,1))$, Wasserstein gradient…

Optimization and Control · Mathematics 2024-08-13 Johannes Hertrich , Robert Beinert , Manuel Gräf , Gabriele Steidl

Generative Adversarial Networks (GANs) have shown impressive performance in generating photo-realistic images. They fit generative models by minimizing certain distance measure between the real image distribution and the generated data…

Machine Learning · Computer Science 2017-09-29 Jianbo Guo , Guangxiang Zhu , Jian Li

Conditional Maximum Mean Discrepancy (CMMD) can capture the discrepancy between conditional distributions by drawing support from nonlinear kernel functions, thus it has been successfully used for pattern classification. However, CMMD does…

Computer Vision and Pattern Recognition · Computer Science 2020-08-25 Chuan-Xian Ren , Pengfei Ge , Dao-Qing Dai , Hong Yan

Among dissimilarities between probability distributions, the Kernel Stein Discrepancy (KSD) has received much interest recently. We investigate the properties of its Wasserstein gradient flow to approximate a target probability distribution…

Machine Learning · Statistics 2021-05-24 Anna Korba , Pierre-Cyril Aubin-Frankowski , Szymon Majewski , Pierre Ablin

The Wasserstein distance is a powerful metric based on the theory of optimal transport. It gives a natural measure of the distance between two distributions with a wide range of applications. In contrast to a number of the common…

Machine Learning · Computer Science 2021-02-16 Jung Hun Oh , Maryam Pouryahya , Aditi Iyer , Aditya P. Apte , Allen Tannenbaum , Joseph O. Deasy

Generating samples from limited information is a fundamental problem across scientific domains. Classical maximum entropy methods provide principled uncertainty quantification from moment constraints but require sampling via MCMC or…

The maximum mean discrepancy (MMD) is a recently proposed test statistic for two-sample test. Its quadratic time complexity, however, greatly hampers its availability to large-scale applications. To accelerate the MMD calculation, in this…

Artificial Intelligence · Computer Science 2015-06-19 Ji Zhao , Deyu Meng

We consider a class of manifolds $\mathcal{M}$ obtained by taking the connected sum of a finite number of $N$-dimensional Riemannian manifolds of the form $(\mathbb{R}^{n_i}, \delta) \times (\mathcal{M}_i, g)$, where $\mathcal{M}_i$ is a…

Analysis of PDEs · Mathematics 2019-12-16 Andrew Hassell , Daniel Nix , Adam Sikora
‹ Prev 1 3 4 5 6 7 10 Next ›