English
Related papers

Related papers: Regularity of the score function in generative mod…

200 papers

In this work, we look at Score-based generative models (also called diffusion generative models) from a geometric perspective. From a new view point, we prove that both the forward and backward process of adding noise and generating from…

Machine Learning · Computer Science 2023-02-10 Sandesh Ghimire , Jinyang Liu , Armand Comas , Davin Hill , Aria Masoomi , Octavia Camps , Jennifer Dy

In performative learning, the data distribution reacts to the deployed model - for example, because strategic users adapt their features to game it - which creates a more complex dynamic than in classical supervised learning. One should…

Machine Learning · Computer Science 2025-10-15 Edwige Cyffers , Alireza Mirrokni , Marco Mondelli

Score-based generative models (SGMs) need to approximate the scores $\nabla \log p_t$ of the intermediate distributions as well as the final distribution $p_T$ of the forward process. The theoretical underpinnings of the effects of these…

Machine Learning · Statistics 2022-10-18 Jakiw Pidstrigach

We consider the class of convex minimization problems, composed of a self-concordant function, such as the $\log\det$ metric, a convex data fidelity term $h(\cdot)$ and, a regularizing -- possibly non-smooth -- function $g(\cdot)$. This…

Machine Learning · Statistics 2014-05-14 Anastasios Kyrillidis , Rabeeh Karimi Mahabadi , Quoc Tran-Dinh , Volkan Cevher

Score-based generative models based on stochastic differential equations (SDEs) achieve impressive performance in sampling from unknown distributions, but often fail to satisfy underlying constraints. We propose a constrained generative…

Machine Learning · Statistics 2025-10-29 Adam Nordenhög , Akash Sharma

Many generative models synthesize data by transforming a standard Gaussian random variable using a deterministic neural network. Among these models are the Variational Autoencoders and the Generative Adversarial Networks. In this work, we…

Machine Learning · Statistics 2022-10-13 Antoine Salmona , Valentin de Bortoli , Julie Delon , Agnès Desolneux

An algorithm is proposed, analyzed, and tested for minimizing locally Lipschitz objective functions that may be nonconvex and/or nonsmooth. The algorithm, which is built upon the gradient-sampling methodology, is designed specifically for…

Optimization and Control · Mathematics 2026-04-02 Albert S. Berahas , Frank E. Curtis , Lara Zebiane

Flow matching has emerged as a powerful framework for generative modeling, offering computational advantages over diffusion models by leveraging deterministic Ordinary Differential Equations (ODEs) instead of stochastic dynamics. While…

Machine Learning · Computer Science 2025-03-13 Chengyue Gong , Xiaoyu Li , Yingyu Liang , Jiangxuan Long , Zhenmei Shi , Zhao Song , Yu Tian

Diffusion models often generate novel samples even when the learned score is only \emph{coarse} -- a phenomenon not accounted for by the standard view of diffusion training as density estimation. In this paper, we show that, under the…

Machine Learning · Computer Science 2026-03-26 Zebang Shen , Ya-Ping Hsieh , Niao He

Score matching is an estimation procedure that has been developed for statistical models whose probability density function is known up to proportionality but whose normalizing constant is intractable, so that maximum likelihood is…

Methodology · Statistics 2024-04-23 Jiazhen Xu , Janice L. Scealy , Andrew T. A. Wood , Tao Zou

Generative diffusion models synthesize new samples by reversing a diffusive process that converts a given data set to generic noise. This is accomplished by training a neural network to match the gradient of the log of the probability…

Machine Learning · Computer Science 2023-10-11 Akhil Premkumar

This work establishes rigorous, novel and widely applicable stability guarantees and transferability bounds for graph convolutional networks -- without reference to any underlying limit object or statistical distribution. Crucially,…

Machine Learning · Computer Science 2023-10-03 Christian Koke

We examine the impact of learning Lipschitz continuous models in the context of model-based reinforcement learning. We provide a novel bound on multi-step prediction error of Lipschitz models where we quantify the error using the…

Machine Learning · Computer Science 2018-07-30 Kavosh Asadi , Dipendra Misra , Michael L. Littman

We present a concise derivation for several influential score-based diffusion models that relies on only a few textbook results. Diffusion models have recently emerged as powerful tools for generating realistic, synthetic signals --…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Chicago Y. Park , Michael T. McCann , Cristina Garcia-Cardona , Brendt Wohlberg , Ulugbek S. Kamilov

Drawing from the theory of stochastic differential equations, we introduce a novel sampling method for known distributions and a new algorithm for diffusion generative models with unknown distributions. Our approach is inspired by the…

Statistics Theory · Mathematics 2024-07-12 Xicheng Zhang

This paper is devoted to the proof of Lipschitz regularity, down to the microscopic scale, for solutions of an elliptic system with highly oscillating coefficients, over a highly oscillating Lipschitz boundary. The originality of this…

Analysis of PDEs · Mathematics 2015-04-08 Carlos Kenig , Christophe Prange

We present theoretical convergence guarantees for ODE-based generative models, specifically flow matching. We use a pre-trained autoencoder network to map high-dimensional original inputs to a low-dimensional latent space, where a…

Machine Learning · Statistics 2024-04-30 Yuling Jiao , Yanming Lai , Yang Wang , Bokai Yan

We study online optimization of smoothed piecewise constant functions over the domain [0, 1). This is motivated by the problem of adaptively picking parameters of learning algorithms as in the recently introduced framework by Gupta and…

Machine Learning · Computer Science 2016-05-23 Vincent Cohen-Addad , Varun Kanade

Machine learning models are increasingly trained or fine-tuned on synthetic data. Recursively training on such data has been observed to significantly degrade performance in a wide range of tasks, often characterized by a progressive drift…

Machine Learning · Statistics 2026-02-19 Nail B. Khelifa , Richard E. Turner , Ramji Venkataramanan

Drifting models train one-step generators by optimizing a kernel-induced mean-shift discrepancy between the data and model distributions, with Laplace kernels used by default in practice. At each point, this discrepancy compares the…

Machine Learning · Computer Science 2026-05-18 Chieh-Hsin Lai , Bac Nguyen , Naoki Murata , Yuhta Takida , Toshimitsu Uesaka , Yuki Mitsufuji , Stefano Ermon , Molei Tao
‹ Prev 1 4 5 6 7 8 10 Next ›