English
Related papers

Related papers: Kernel-Gradient Drifting Models

200 papers

Generative Modeling via Drifting has recently achieved state-of-the-art one-step image generation through a kernel-based drift operator, yet the success is largely empirical and its theoretical foundations remain poorly understood. In this…

Machine Learning · Computer Science 2026-03-11 Erkan Turan , Maks Ovsjanikov

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

Generative modeling can be formulated as learning a mapping f such that its pushforward distribution matches the data distribution. The pushforward behavior can be carried out iteratively at inference time, for example in diffusion and…

Machine Learning · Computer Science 2026-02-09 Mingyang Deng , He Li , Tianhong Li , Yilun Du , Kaiming He

We establish a theoretical link between the recently proposed "drifting" generative dynamics and gradient flows induced by the Sinkhorn divergence. In a particle discretization, the drift field admits a cross-minus-self decomposition: an…

Machine Learning · Computer Science 2026-03-30 Ping He , Om Khangaonkar , Hamed Pirsiavash , Yikun Bai , Soheil Kolouri

Drifting models have recently gained attention for generating high-quality samples in a single forward pass. During training, they learn a push-forward map by following a vector-valued field, the drift field. We ask whether this procedure…

Machine Learning · Computer Science 2026-05-11 Leonard T. Franz , Sebastian Hoffmann , Tim Weiland , Bernhard Schölkopf , Georg Martius

We reveal a precise mathematical framework about a new family of generative models which we call Gradient Flow Drifting. With this framework, we prove an equivalence between the recently proposed Drifting Model and the Wasserstein gradient…

Machine Learning · Computer Science 2026-03-12 Jiarui Cao , Zixuan Wei , Yuxin Liu

Sampling molecular conformations from the Boltzmann distribution is essential for computational chemistry, but iterative diffusion methods are prohibitively slow. Drifting Models offer one-step generation, yet their equilibrium matches the…

Chemical Physics · Physics 2026-03-09 Pipi Hu

Drifting Models have emerged as a new paradigm for one-step generative modeling, achieving strong image quality without iterative inference. The premise is to replace the iterative denoising process in diffusion models with a single…

Machine Learning · Computer Science 2026-05-13 Ali Falahati , Elliot Creager , Gautam Kamath , Shubhankar Mohapatra

We consider learning on graphs, guided by kernels that encode similarity between vertices. Our focus is on random walk kernels, the analogues of squared exponential kernels in Euclidean spaces. We show that on large, locally treelike,…

Machine Learning · Statistics 2013-10-01 Matthew Urry , Peter Sollich

Gaussian Process regression is a kernel method successfully adopted in many real-life applications. Recently, there is a growing interest on extending this method to non-Euclidean input spaces, like the one considered in this paper,…

Machine Learning · Computer Science 2022-12-05 Antonio Candelieri , Andrea Ponti , Francesco Archetti

This paper studies the identifiability and stability of drifting fields within the framework of Generative Modeling via Drifting. The motivating question is whether a zero-drift equilibrium identifies the target distribution, and whether an…

Machine Learning · Statistics 2026-05-13 HakGeun Lee , Hyonho Chun

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 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

Guiding unconditional diffusion models typically requires either retraining with conditional inputs or per-step gradient computations (e.g., classifier-based guidance), both of which incur substantial computational overhead. We present a…

Machine Learning · Computer Science 2026-02-13 Qingsong Wang , Mikhail Belkin , Yusu Wang

Bayesian inference problems require sampling or approximating high-dimensional probability distributions. The focus of this paper is on the recently introduced Stein variational gradient descent methodology, a class of algorithms that rely…

Machine Learning · Statistics 2023-02-14 A. Duncan , N. Nuesken , L. Szpruch

Modeling geophysical processes as low-dimensional dynamical systems and regressing their vector field from data is a promising approach for learning emulators of such systems. We show that when the kernel of these emulators is also learned…

Atmospheric and Oceanic Physics · Physics 2021-08-11 Boumediene Hamzi , Romit Maulik , Houman Owhadi

Dataset distillation aims to synthesize a compact subset of the original data, enabling models trained on it to achieve performance comparable to those trained on the original large dataset. Existing distribution-matching methods are…

Computer Vision and Pattern Recognition · Computer Science 2025-12-11 Xuhui Li , Zhengquan Luo , Zihui Cui , Zhiqiang Xu

Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updates. We introduce W-Flow, a framework for training a…

Machine Learning · Computer Science 2026-05-28 Jiaqi Han , Puheng Li , Qiushan Guo , Renyuan Xu , Stefano Ermon , Emmanuel J. Candès

Quantum computing offers fundamentally more expressive mechanisms for generative modeling, yet current approaches remain constrained by classical neural components that bottleneck quantum capability and hardware efficiency. We propose the…

Quantum Physics · Physics 2025-10-06 Yihua Li , Jiayi Chen , Tamanna S. Kumavat , Kyriakos Flouris

We develop a unified theoretical framework for data-free one-step sampling from unnormalized target distributions based on Wasserstein gradient flows. For a broad class of standard f-divergence objectives, we show that the induced velocity…

Machine Learning · Computer Science 2026-05-19 Chenguang Wang , Tianshu Yu
‹ Prev 1 2 3 10 Next ›