paper-with-me

Papers

Online Posterior Sampling with a Diffusion Prior

2024-10-04 · Branislav Kveton, Boris Oreshkin, Youngsuk Park, Aniket Deshmukh, Rui Song

Posterior sampling in contextual bandits with a Gaussian prior can be implemented exactly or approximately using the Laplace approximation. The Gaussian prior is computationally efficient but it cannot describe complex distributions. In this work, we propose approximate posterior sampling algorithms for contextual bandits with a diffusion model prior. The key idea is to sample from a chain of approximate conditional posteriors, one for each stage of the reverse process, which are estimated in a closed form using the Laplace approximation. Our approximations are motivated by posterior sampling with a Gaussian prior, and inherit its simplicity and efficiency. They are asymptotically consistent and perform well empirically on a variety of contextual bandit problems.

📄 PDF Abstract BibTeX arXiv:2410.03919

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Armed Bandits

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…

Similar Papers 제목 키워드 기반

CT Reconstruction using Diffusion Posterior Sampling conditioned on a Nonlinear Measurement Model

2023-12-03 · Shudong Li, Xiao Jiang, Matthew Tivnan, Grace J. Gang 외

Diffusion models have been demonstrated as powerful deep learning tools for image generation in CT reconstruction and restoration. Recently, diffusion posterior sampling, where a score-based diffusion prior is combined w…

CT ReconstructionImage GenerationImage Reconstruction

An Efficient Conditional Score-based Filter for High Dimensional Nonlinear Filtering Problems

2025-09-24 · Zhijun Zeng, Weiye Gan, Junqing Chen, Zuoqiang Shi arxiv

In many engineering and applied science domains, high-dimensional nonlinear filtering is still a challenging problem. Recent advances in score-based diffusion models offer a promising alternative for posterior sampling b…

Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements

2024-11-15 · Shijie Zhou, Huaisheng Zhu, Rohan Sharma, Ruiyi Zhang 외

Diffusion models have emerged as a powerful foundation model for visual generation. With an appropriate sampling process, it can effectively serve as a generative prior to solve general inverse problems. Current posterio…

DeblurringDenoisingSuper-Resolution

A Stabilized Path-Space Approach to Diffusion-Based Posterior Sampling

2026-06-10 · Evan Scope Crafts, Umberto Villa, Saviz Mowlavi, Yanting Ma 외 arxiv

Diffusion models provide expressive data-driven priors for Bayesian inverse problems, but many diffusion posterior samplers rely on heuristic guidance approximations that can fail for nonlinear operators and multimodal p…

When, why, and how do diffusion posterior samplers fail? A finite-sample lens

2026-05-28 · Benjamin A. Burns, Sara Fridovich-Keil arxiv

Diffusion models have excellent capacity to model complex distributions of natural data, which has made them a popular and effective choice for posterior sampling in imaging inverse problems. Existing methods can incorpo…