English
Related papers

Related papers: Numerical Analysis on Neural Network Projected Sch…

200 papers

Many applications in machine learning involve data represented as probability distributions. The emergence of such data requires radically novel techniques to design tractable gradient flows on probability distributions over this type of…

Machine Learning · Computer Science 2025-06-10 Clément Bonet , Christophe Vauthier , Anna Korba

Wasserstein distributionally robust optimization offers a framework for model fitting in machine learning under potential shifts in the data distribution. We study a regularized variant of this problem in which entropic smoothing produces a…

Optimization and Control · Mathematics 2026-05-28 Tam Le

Neural Processes (NPs) are a class of models that learn a mapping from a context set of input-output pairs to a distribution over functions. They are traditionally trained using maximum likelihood with a KL divergence regularization term.…

Machine Learning · Computer Science 2020-01-13 Andrew Carr , Jared Nielsen , David Wingate

We study a natural Wasserstein gradient flow on manifolds of probability distributions with discrete sample spaces. We derive the Riemannian structure for the probability simplex from the dynamical formulation of the Wasserstein distance on…

Optimization and Control · Mathematics 2021-04-19 Wuchen Li , Guido Montufar

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

We develop novel neural network-based implicit particle methods to compute high-dimensional Wasserstein-type gradient flows with linear and nonlinear mobility functions. The main idea is to use the Lagrangian formulation in the…

Numerical Analysis · Mathematics 2023-11-14 Wonjun Lee , Li Wang , Wuchen Li

We propose a variational scheme for computing Wasserstein gradient flows. The scheme builds upon the Jordan--Kinderlehrer--Otto framework with the Benamou-Brenier's dynamic formulation of the quadratic Wasserstein metric and adds a…

Numerical Analysis · Mathematics 2020-07-15 Wuchen Li , Jianfeng Lu , Li Wang

As a counterpoint to recent numerical methods for crystal surface evolution, which agree well with microscopic dynamics but suffer from significant stiffness that prevents simulation on fine spatial grids, we develop a new numerical method…

Numerical Analysis · Mathematics 2020-06-24 Katy Craig , Jian-Guo Liu , Jianfeng Lu , Jeremy L. Marzuola , Li Wang

Variational inference is a technique that approximates a target distribution by optimizing within the parameter space of variational families. On the other hand, Wasserstein gradient flows describe optimization within the space of…

Machine Learning · Statistics 2023-11-01 Mingxuan Yi , Song Liu

In this work, we propose a numerical method to compute the Wasserstein Hamiltonian flow (WHF), which is a Hamiltonian system on the probability density manifold. Many well-known PDE systems can be reformulated as WHFs. We use parameterized…

Numerical Analysis · Mathematics 2023-07-18 Hao Wu , Shu Liu , Xiaojing Ye , Haomin Zhou

The paper contains approximation guarantees for neural networks that are trained with gradient flow, with error measured in the continuous $L_2(\mathbb{S}^{d-1})$-norm on the $d$-dimensional unit sphere and targets that are Sobolev smooth.…

Machine Learning · Computer Science 2023-09-12 G. Welper

Compressing large Neural Networks (NN) by quantizing the parameters, while maintaining the performance is highly desirable due to reduced memory and time complexity. In this work, we cast NN quantization as a discrete labelling problem, and…

Computer Vision and Pattern Recognition · Computer Science 2019-08-21 Thalaiyasingam Ajanthan , Puneet K. Dokania , Richard Hartley , Philip H. S. Torr

The training of artificial neural networks (ANNs) is nowadays a highly relevant algorithmic procedure with many applications in science and industry. Roughly speaking, ANNs can be regarded as iterated compositions between affine linear…

Optimization and Control · Mathematics 2022-07-14 Simon Eberle , Arnulf Jentzen , Adrian Riekert , Georg Weiss

This paper develops expansive gradient dynamics in deep neural network-induced mapping spaces. Specifically, we generate tools and concepts for minimizing a class of energy functionals in an abstract Hilbert space setting covering a wide…

Optimization and Control · Mathematics 2025-07-21 Wolfgang Dahmen , Wuchen Li , Yuankai Teng , Zhu Wang

The training of artificial neural networks (ANNs) with rectified linear unit (ReLU) activation via gradient descent (GD) type optimization schemes is nowadays a common industrially relevant procedure. Till this day in the scientific…

Machine Learning · Computer Science 2023-04-13 Simon Eberle , Arnulf Jentzen , Adrian Riekert , Georg S. Weiss

We present a novel approximate inference method for diffusion processes, based on the Wasserstein gradient flow formulation of the diffusion. In this formulation, the time-dependent density of the diffusion is derived as the limit of…

Machine Learning · Statistics 2018-06-13 Charlie Frogner , Tomaso Poggio

We provide gradient flow interpretations for the continuous-time continuous-state Hopfield neural network (HNN). The ordinary and stochastic differential equations associated with the HNN were introduced in the literature as analog…

Optimization and Control · Mathematics 2019-11-15 Abhishek Halder , Kenneth F. Caluya , Bertrand Travacca , Scott J. Moura

This manuscript introduces a regression-type formulation for approximating the Perron-Frobenius Operator by relying on distributional snapshots of data. These snapshots may represent densities of particles. The Wasserstein metric is…

Optimization and Control · Mathematics 2020-11-03 Amirhossein Karimi , Tryphon T. Georgiou

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

It is well understood that neural networks with carefully hand-picked weights provide powerful function approximation and that they can be successfully trained in over-parametrized regimes. Since over-parametrization ensures zero training…

Machine Learning · Computer Science 2024-05-21 G. Welper