English
Related papers

Related papers: Gradient Flow Drifting: Generative Modeling via Wa…

200 papers

Knowledge distillation (KD) is an essential technique to compress large language models (LLMs) into smaller ones. However, despite the distinct roles of the student model and the teacher model in KD, most existing frameworks still use a…

Computation and Language · Computer Science 2026-03-25 Songming Zhang , Xue Zhang , Tong Zhang , Bojie Hu , Yufeng Chen , Jinan Xu

This study focuses on a Wasserstein-type gradient flow, which represents an optimization process of a continuous model of a Deep Neural Network (DNN). First, we establish the existence of a minimizer for an average loss of the model under…

Machine Learning · Computer Science 2024-04-16 Noboru Isobe

Sampling a probability distribution with an unknown normalization constant is a fundamental problem in computational science and engineering. This task may be cast as an optimization problem over all probability measures, and an initial…

Machine Learning · Statistics 2024-09-12 Yifan Chen , Daniel Zhengyu Huang , Jiaoyang Huang , Sebastian Reich , Andrew M. Stuart

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 maximum mean discrepancy…

Machine Learning · Statistics 2025-04-14 Viktor Stein , Sebastian Neumayer , Nicolaj Rux , Gabriele Steidl

Stein Variational Gradient Descent (SVGD) is a deterministic interacting-particle method for sampling from a target probability measure given access to its score function. In the mean-field and continuous-time limit, it is known that the…

Machine Learning · Statistics 2026-05-12 Lénaïc Chizat , Maria Colombo , Roberto Colombo , Xavier Fernández-Real

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 estimator), solves a…

Machine Learning · Statistics 2021-11-01 Pierre Glaser , Michael Arbel , Arthur Gretton

High-dimensional generative modeling is fundamentally a manifold-learning problem: real data concentrate near a low-dimensional structure embedded in the ambient space. Effective generators must therefore balance support fidelity -- placing…

Machine Learning · Statistics 2026-02-24 Xinyu Tian , Xiaotong Shen

The $E$-optimality criterion for a regression model maximizes the smallest eigenvalue of the information matrix and becomes non-differentiable when this eigenvalue has multiplicity greater than one. Working in the $2$-Wasserstein space, we…

Optimization and Control · Mathematics 2026-04-17 Jieling Shi , Kim-Chuan Toh , Xin T. Tong , Weng Kee Wong

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2019-04-16 Jiqing Wu , Zhiwu Huang , Dinesh Acharya , Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool

In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions. Unfortunately, it is challenging to approximate the WD of high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2019-04-17 Jiqing Wu , Zhiwu Huang , Dinesh Acharya , Wen Li , Janine Thoma , Danda Pani Paudel , Luc Van Gool

With the rapidly growing model complexity and data volume, training deep generative models (DGMs) for better performance has becoming an increasingly more important challenge. Previous research on this problem has mainly focused on…

Machine Learning · Computer Science 2021-12-08 Yufan Zhou , Chunyuan Li , Changyou Chen , Jinhui Xu

Purely dissipative evolution equations are often cast as gradient flow structures, $\dot{\mathbf{z}}=K(\mathbf{z})DS(\mathbf{z})$, where the variable $\mathbf{z}$ of interest evolves towards the maximum of a functional $S$ according to a…

Mathematical Physics · Physics 2015-11-18 Celia Reina , Johannes Zimmer

In this paper we bring together some of the key ideas and methods of two disparate fields of mathematical research, frame theory and optimal transport, using the methods of the second to answer questions posed in the first. In particular,…

Functional Analysis · Mathematics 2022-12-01 Clare Wickman , Kasso Okoudjou

We introduce a generative learning framework to model high-dimensional parametric systems using gradient guidance and virtual observations. We consider systems described by Partial Differential Equations (PDEs) discretized with structured…

Machine Learning · Computer Science 2024-08-02 Han Gao , Sebastian Kaltenbach , Petros Koumoutsakos

Among generative neural models, flow matching techniques stand out for their simple applicability and good scaling properties. Here, velocity fields of curves connecting a simple latent and a target distribution are learned. Then the…

Machine Learning · Computer Science 2026-04-27 Christian Wald , Gabriele Steidl

Wasserstein gradient flows (WGFs) describe the evolution of probability distributions in Wasserstein space as steepest descent dynamics for a free energy functional. Computing the full path from an arbitrary initial distribution to…

Machine Learning · Computer Science 2026-04-14 Chengyu Liu , Xiang Zhou

In this paper, we study higher-order-accurate-in-time minimizing movements schemes for Wasserstein gradient flows. We introduce a novel accelerated second-order scheme, leveraging the differential structure of the Wasserstein space in both…

Analysis of PDEs · Mathematics 2025-12-23 Raymond Chu , Matt Jacobs

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

Flow-based generative models can be viewed through a physics lens: sampling transports a particle from noise to data by integrating a time-varying velocity field, and each sample corresponds to a trajectory with its own dynamical effort.…

Machine Learning · Computer Science 2026-02-10 Ziyun Li , Huancheng Hu , Soon Hoe Lim , Xuyu Li , Fei Gao , Enmao Diao , Zezhen Ding , Michalis Vazirgiannis , Henrik Bostrom

Pretraining on large-scale collections of PDE-governed spatiotemporal trajectories has recently shown promise for building generalizable models of dynamical systems. Yet most existing PDE foundation models rely on deterministic Transformer…

Machine Learning · Computer Science 2026-04-21 Zituo Chen , Sili Deng
‹ Prev 1 4 5 6 7 8 10 Next ›