paper-with-me

홈 › Papers

Importance Sampling via Score-based Generative Models

2025-02-07 · Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo de Veciana

Importance sampling, which involves sampling from a probability density function (PDF) proportional to the product of an importance weight function and a base PDF, is a powerful technique with applications in variance reduction, biased or customized sampling, data augmentation, and beyond. Inspired by the growing availability of score-based generative models (SGMs), we propose an entirely training-free Importance sampling framework that relies solely on an SGM for the base PDF. Our key innovation is realizing the importance sampling process as a backward diffusion process, expressed in terms of the score function of the base PDF and the specified importance weight function--both readily available--eliminating the need for any additional training. We conduct a thorough analysis demonstrating the method's scalability and effectiveness across diverse datasets and tasks, including importance sampling for industrial and natural images with neural importance weight functions. The training-free aspect of our method is particularly compelling in real-world scenarios where a single base distribution underlies multiple biased sampling tasks, each requiring a different importance weight function. To the best of our knowledge our approach is the first importance sampling framework to achieve this.

📄 PDF Abstract BibTeX arXiv:2502.04646

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
BASE 설명 없음

Similar Papers 제목 키워드 기반

Score-Regularized Joint Sampling with Importance Weights for Flow Matching

2025-11-21 · Xinshuang Liu, Runfa Blark Li, Shaoxiu Wei, Truong Nguyen arxiv

Flow matching models effectively represent complex distributions, yet estimating expectations of functions of their outputs remains challenging under limited sampling budgets. Independent sampling often yields high-varia…

REPS: Reconstruction-based Point Cloud Sampling

2024-03-08 · Guoqing Zhang, Wenbo Zhao, Jian Liu, Xianming Liu

Sampling is widely used in various point cloud tasks as it can effectively reduce resource consumption. Recently, some methods have proposed utilizing neural networks to optimize the sampling process for various task req…

Score-Based Diffusion meets Annealed Importance Sampling

2022-08-16 · Arnaud Doucet, Will Grathwohl, Alexander G. D. G. Matthews, Heiko Strathmann

More than twenty years after its introduction, Annealed Importance Sampling (AIS) remains one of the most effective methods for marginal likelihood estimation. It relies on a sequence of distributions interpolating betwe…

Manifold-Aligned Generative Transport

2026-02-23 · Xinyu Tian, Xiaotong Shen arxiv

High-dimensional generative modeling is fundamentally a manifold-learning problem: real data concentrate near a low-dimensional structure embedded in the ambient space. Effective generators must therefore balance support…

Learning Deep Generative Models with Annealed Importance Sampling

2019-06-12 · Xinqiang Ding, David J. Freedman

Variational inference (VI) and Markov chain Monte Carlo (MCMC) are two main approximate approaches for learning deep generative models by maximizing marginal likelihood. In this paper, we propose using annealed importanc…

Variational Inference