English
Related papers

Related papers: Generative Drifting is Secretly Score Matching: a …

200 papers

Generative models which use explicit density modeling (e.g., variational autoencoders, flow-based generative models) involve finding a mapping from a known distribution, e.g. Gaussian, to the unknown input distribution. This often requires…

Machine Learning · Computer Science 2021-12-02 Zhichun Huang , Rudrasis Chakraborty , Vikas Singh

Score matching has become a central training objective in modern generative modeling, particularly in diffusion models, where it is used to learn high-dimensional data distributions through the estimation of score functions. Despite its…

Machine Learning · Computer Science 2025-12-01 Yiran Zhang , Weihang Xu , Mo Zhou , Maryam Fazel , Simon Shaolei Du

We give an improved theoretical analysis of score-based generative modeling. Under a score estimate with small $L^2$ error (averaged across timesteps), we provide efficient convergence guarantees for any data distribution with second-order…

Machine Learning · Computer Science 2023-02-03 Hongrui Chen , Holden Lee , Jianfeng Lu

We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching. Because gradients can be ill-defined and hard to estimate when the data resides on…

Machine Learning · Computer Science 2020-10-13 Yang Song , Stefano Ermon

These lecture notes introduce the statistical analysis of continuous-time generative models built from Markov dynamics. We begin with the stochastic-calculus foundations of score-based diffusion models, including time reversal, score…

Statistics Theory · Mathematics 2026-04-27 Eddie Aamari , Arthur Stéphanovitch

We develop a kernel method for generative modeling within the stochastic interpolant framework, replacing neural network training with linear systems. The drift of the generative SDE is $\hat b_t(x) = \nabla\phi(x)^\top\eta_t$, where…

Most existing generative models are limited to learning a single probability distribution from the training data and cannot generalize to novel distributions for unseen data. An architecture that can generate samples from both trained…

Machine Learning · Computer Science 2024-10-16 Xinyu Liao , Aoyang Qin , Jacob Seidman , Junqi Wang , Wei Wang , Paris Perdikaris

Distribution Matching Distillation (DMD) is a widely used paradigm for accelerating inference in few-step video diffusion models. However, DMD-style video distillation faces two coupled challenges: the fake score must track a continuously…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Zhuguanyu Wu , Ruihao Gong , Yang Yong , Yushi Huang , Xiangyu Fan , Lei Yang , Dahua Lin , Xianglong Liu

Supervised learning models are one of the most fundamental classes of models. Viewing supervised learning from a probabilistic perspective, the set of training data to which the model is fitted is usually assumed to follow a stationary…

Machine Learning · Statistics 2022-09-14 Kungang Zhang , Anh T. Bui , Daniel W. Apley

Several machine learning applications involve the optimization of higher-order derivatives (e.g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation. As a…

Machine Learning · Computer Science 2020-11-26 Tianyu Pang , Kun Xu , Chongxuan Li , Yang Song , Stefano Ermon , Jun Zhu

Uncertain changes in data streams present challenges for machine learning models to dynamically adapt and uphold performance in real-time. Particularly, classification boundary change, also known as real concept drift, is the major cause of…

Machine Learning · Computer Science 2024-05-24 Feng Gu , Jie Lu , Zhen Fang , Kun Wang , Guangquan Zhang

We propose and analyze a conservative drifting method for one-step generative modeling. The method replaces the original displacement-based drifting velocity by a kernel density estimator (KDE)-gradient velocity, namely the difference of…

Machine Learning · Statistics 2026-05-26 Krishnakumar Balasubramanian

Diffusion-based trajectory planners can synthesize rich, multimodal action sequences for offline reinforcement learning, but their iterative denoising incurs substantial inference-time cost, making closed-loop planning slow under tight…

Robotics · Computer Science 2026-03-17 Gokul Puthumanaillam , Melkior Ornik

Kernel continual learning by \citet{derakhshani2021kernel} has recently emerged as a strong continual learner due to its non-parametric ability to tackle task interference and catastrophic forgetting. Unfortunately its success comes at the…

Machine Learning · Computer Science 2021-12-28 Mohammad Mahdi Derakhshani , Xiantong Zhen , Ling Shao , Cees G. M. Snoek

We consider the problem of generative modeling based on smoothing an unknown density of interest in $\mathbb{R}^d$ using factorial kernels with $M$ independent Gaussian channels with equal noise levels introduced by Saremi and Srivastava…

Machine Learning · Statistics 2023-03-22 Saeed Saremi , Rupesh Kumar Srivastava , Francis Bach

Smoothed functional (SF) schemes for gradient estimation are known to be efficient in stochastic optimization algorithms, specially when the objective is to improve the performance of a stochastic system. However, the performance of these…

Information Theory · Computer Science 2014-07-04 Debarghya Ghoshdastidar , Ambedkar Dukkipati , Shalabh Bhatnagar

Diffusion models generate high-quality synthetic data. They operate by defining a continuous-time forward process which gradually adds Gaussian noise to data until fully corrupted. The corresponding reverse process progressively "denoises"…

Directional data consist of observations distributed on a (hyper)sphere, and appear in many applied fields, such as astronomy, ecology, and environmental science. This paper studies both statistical and computational problems of kernel…

Machine Learning · Statistics 2021-10-18 Yikun Zhang , Yen-Chi Chen

We establish a bridge between spectral clustering and Gromov-Wasserstein Learning (GWL), a recent optimal transport-based approach to graph partitioning. This connection both explains and improves upon the state-of-the-art performance of…

Machine Learning · Computer Science 2021-03-04 Samir Chowdhury , Tom Needham

Larger and deeper networks generalise well despite their increased capacity to overfit. Understanding why this happens is theoretically and practically important. One recent approach looks at the infinitely wide limits of such networks and…

Machine Learning · Computer Science 2023-10-13 Adrian Goldwaser , Hong Ge