The paper introduces a generalized score matching objective for parameter estimation on convex subsets of ρ^d, derived from Minimum Probability Flow learning. It shows that this objective is a proper local scoring rule of second order, ensuring recovery of the true density when minimized, and proves convexity and consistency for exponential family models under standard conditions. Experiments demonstrate the method’s effectiveness on constrained domains where the partition function is intractable, including a generative modeling use‑case.
By Nishanth Shetty, Saisuchith Mahajan, Chandra Sekhar Seelamantula
arXiv:2606. 19876v1 Announce Type: new Abstract: The score matching problem is a central training objective in modern generative modeling, diffusion models, fitting unnormalized statistical models, and inverse problems.
By Alexander Tyurin
arXiv:2610. 02663v1 Announce Type: cross Abstract: Despite the remarkable empirical success of flow-matching models, their statistical generalization guarantees remain underdeveloped.
By Saptarshi Chakraborty, Quentin Berthet, Peter L. Bartlett
arXiv:2504.05161v2 Announce Type: replace-cross
Abstract: Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key...
By Sinho Chewi, Alkis Kalavasis, Anay Mehrotra, Omar Montasser
arXiv:2511. 03963v3 Announce Type: replace-cross Abstract: We introduce a density-power weighted variant of the Stein operator, called the $\gamma$-Stein operator, for robust inference with unnormalized probability models.
By Shinto Eguchi
arXiv:2610.07228v1 Announce Type: cross
Abstract: Natural gradient descent (NGD) underlies common methods in ML. For dually flat families, idealized NGD on the forward Kullback--Leibler objective fol...
By Guni Sharon, Alan Kuhnle
arXiv:2606. 18306v1 Announce Type: new Abstract: Gaussian width is a central geometric complexity measure in high-dimensional probability, compressed sensing, convex optimization, and learning theory.
By Vu Khac Ky
arXiv:2506. 06542v2 Announce Type: replace-cross Abstract: We study the problem of likelihood maximization when the likelihood function is intractable but model simulations are readily available.
By Sherman Khoo, Yakun Wang, Song Liu, Mark Beaumont
arXiv:2609. 38412v1 Announce Type: cross Abstract: We propose a novel local-polynomial estimator of the ratio $r=f/g$ of two $d$-dimensional densities $f$ and $g$, from which independent samples are available.
By Hajo Holzmann, Alexander Meister
arXiv:2609.38547v1 Announce Type: cross
Abstract: Defining a weighted mean over probability measures under probability metrics is a central tool in probabilistic machine learning. Under the Wasserste...
By Eduardo Fernandes Montesuma
arXiv:2508. 01597v2 Announce Type: replace Abstract: Score Matching (SM) is a powerful framework for estimating the log-density derivatives of a distribution without calculating its normalizing constants.
By Juyan Zhang, Rhys Newbury, Xinyang Zhang, Tin Tran, Dana Kulic, Michael Burke
arXiv:2608.23916v1 Announce Type: new
Abstract: Denoising score matching trains diffusion models by regressing onto a conditional score, although generation ultimately requires the marginal score. Th...
By Avinash Raju, Kai Zhang