English
Related papers

Related papers: Convergence analysis of OT-Flow for sample generat…

200 papers

Finding a transformation between two unknown probability distributions from finite samples is crucial for modeling complex data distributions and performing tasks such as sample generation, domain adaptation and statistical inference. One…

Machine Learning · Computer Science 2024-07-11 Zhe Xiong , Qiaoqiao Ding , Xiaoqun Zhang

We introduce the proximal optimal transport divergence, a novel discrepancy measure that interpolates between information divergences and optimal transport distances via an infimal convolution formulation. This divergence provides a…

Optimization and Control · Mathematics 2025-08-11 Ricardo Baptista , Panagiota Birmpa , Markos A. Katsoulakis , Luc Rey-Bellet , Benjamin J. Zhang

The AC Optimal Power Flow (AC-OPF) is a key building block in many power system applications. It determines generator setpoints at minimal cost that meet the power demands while satisfying the underlying physical and operational…

Signal Processing · Electrical Eng. & Systems 2020-07-01 Minas Chatzos , Ferdinando Fioretto , Terrence W. K. Mak , Pascal Van Hentenryck

Fast and accurate generation of molecular conformers is desired for downstream computational chemistry and drug discovery tasks. Currently, training and sampling state-of-the-art diffusion or flow-based models for conformer generation…

In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization. To do so, we first interpret momentum as solving an $\ell_2$-regularized…

Machine Learning · Computer Science 2019-06-04 Ziming Zhang , Wenju Xu , Alan Sullivan

Despite their empirical success, the internal mechanism by which transformer models align tokens during language processing remains poorly understood. This paper provides a mechanistic and theoretical explanation of token alignment in LLMs.…

Machine Learning · Computer Science 2025-12-19 Hadi Daneshmand

Optimal Transport (OT) distances such as Wasserstein have been used in several areas such as GANs and domain adaptation. OT, however, is very sensitive to outliers (samples with large noise) in the data since in its objective function,…

Machine Learning · Computer Science 2020-10-13 Yogesh Balaji , Rama Chellappa , Soheil Feizi

This paper develops algorithms for high-dimensional stochastic control problems based on deep learning and dynamic programming. Unlike classical approximate dynamic programming approaches, we first approximate the optimal policy by means of…

Probability · Mathematics 2021-09-21 Côme Huré , Huyên Pham , Achref Bachouch , Nicolas Langrené

Flow-matching models provide a powerful framework for various applications, offering efficient sampling and flexible probability path modeling. These models are characterized by flows with low curvature in learned generative trajectories,…

Machine Learning · Computer Science 2025-01-22 Zibin Wang , Zhiyuan Ouyang , Xiangyun Zhang

Conditional Flow Matching (CFM), a simulation-free method for training continuous normalizing flows, provides an efficient alternative to diffusion models for key tasks like image and video generation. The performance of CFM in solving…

Machine Learning · Computer Science 2026-03-17 Aram Davtyan , Leello Tadesse Dadi , Volkan Cevher , Paolo Favaro

Rectified flow (Liu et al., 2022; Liu, 2022; Wu et al., 2023) is a method for defining a transport map between two distributions, and enjoys popularity in machine learning, although theoretical results supporting the validity of these…

Statistics Theory · Mathematics 2025-12-11 Gonzalo Mena , Arun Kumar Kuchibhotla , Larry Wasserman

This paper considers the problem of unconstrained minimization of smooth convex functions having Lipschitz continuous gradients with known Lipschitz constant. We recently proposed an optimized gradient method (OGM) for this problem and…

Optimization and Control · Mathematics 2019-06-14 Donghwan Kim , Jeffrey A. Fessler

Achieving a balance between image quality (precision) and diversity (recall) is a significant challenge in the domain of generative models. Current state-of-the-art models primarily rely on optimizing heuristics, such as the Fr\'echet…

Machine Learning · Computer Science 2023-11-02 Alexandre Verine , Benjamin Negrevergne , Muni Sreenivas Pydi , Yann Chevaleyre

The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensional) partial differential equations (PDEs). We decompose the generalization…

Numerical Analysis · Mathematics 2026-02-26 Chenguang Liu , Antonis Papapantoleon , Jasper Rou

Optimal transport (OT) is a versatile framework for comparing probability measures, with many applications to statistics, machine learning, and applied mathematics. However, OT distances suffer from computational and statistical scalability…

Statistics Theory · Mathematics 2022-06-08 Ziv Goldfeld , Kengo Kato , Gabriel Rioux , Ritwik Sadhu

Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formulations have been extensively used in a variety of supervised…

Computer Vision and Pattern Recognition · Computer Science 2023-12-19 Deen Dayal Mohan , Bhavin Jawade , Srirangaraj Setlur , Venu Govindaraj

Flow matching has emerged as a powerful generative modeling approach with flexible choices of source distribution. While Gaussian distributions are commonly used, the potential for better alternatives in high-dimensional data generation…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Junho Lee , Kwanseok Kim , Joonseok Lee

Modern stochastic optimization pipelines increasingly rely on learned generative models to represent uncertainty, while downstream decisions are evaluated almost entirely through Monte Carlo scenarios. This shifts the operational object of…

Optimization and Control · Mathematics 2026-05-01 Ziwei Zhang , Jonathan Yu-Meng Li

A key challenge in modern deep learning theory is to explain the remarkable success of gradient-based optimization methods when training large-scale, complex deep neural networks. Though linear convergence of such methods has been proved…

Machine Learning · Computer Science 2025-09-30 Yash Jakhmola

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