paper-with-me

홈 › Papers

Heavy-tailed denoising score matching

2021-12-17 · Jacob Deasy, Nikola Simidjievski, Pietro Liò

Score-based model research in the last few years has produced state of the art generative models by employing Gaussian denoising score-matching (DSM). However, the Gaussian noise assumption has several high-dimensional limitations, motivating a more concrete route toward even higher dimension PDF estimation in future. We outline this limitation, before extending the theory to a broader family of noising distributions -- namely, the generalised normal distribution. To theoretically ground this, we relax a key assumption in (denoising) score matching theory, demonstrating that distributions which are differentiable almost everywhere permit the same objective simplification as Gaussians. For noise vector norm distributions, we demonstrate favourable concentration of measure in the high-dimensional spaces prevalent in deep learning. In the process, we uncover a skewed noise vector norm distribution and develop an iterative noise scaling algorithm to consistently initialise the multiple levels of noise in annealed Langevin dynamics (LD). On the practical side, our use of heavy-tailed DSM leads to improved score estimation, controllable sampling convergence, and more balanced unconditional generative performance for imbalanced datasets.

📄 PDF Abstract BibTeX arXiv:2112.09788

Code (1)

jacobdeasy/heavy-tail-dsm 공식 구현 pytorch

Tasks

Denoising

Similar Papers 제목 키워드 기반

Heavy-Tailed Diffusion Models

2024-10-18 · Kushagra Pandey, Jaideep Pathak, Yilun Xu, Stephan Mandt 외

Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In this work, we show that traditi…

Denoising

Denoising Lévy Probabilistic Models

2024-07-26 · Dario Shariatian, Umut Simsekli, Alain Durmus

Investigating noise distribution beyond Gaussian in diffusion generative models is an open problem. The Gaussian case has seen success experimentally and theoretically, fitting a unified SDE framework for score-based and…

Denoising

Score-based Generative Models with Lévy Processes

2023-09-21 · NeurIPS 2023 11

Investigating the optimal stochastic process beyond Gaussian for noise injection in a score-based generative model remains an open question. Brownian motion is a light-tailed process with continuous paths, which leads to…

A diffusion-based generative model for financial time series via geometric Brownian motion

2025-07-25 · Gihun Kim, Sun-Yong Choi, Yeoneung Kim arxiv

We propose a novel diffusion-based generative framework for financial time series that incorporates geometric Brownian motion (GBM), the foundation of the Black--Scholes theory, into the forward noising process. Unlike s…

Mirror Flow Matching with Heavy-Tailed Priors for Generative Modeling on Convex Domains

2025-10-10 · Yunrui Guan, Krishnakumar Balasubramanian, Shiqian Ma arxiv

We study generative modeling on convex domains using flow matching and mirror maps, and identify two fundamental challenges. First, standard log-barrier mirror maps induce heavy-tailed dual distributions, leading to ill-…