Posterior Sampling

Posterior sampling aims to efficiently generate samples from a probability distribution representing the posterior belief about unknown parameters given observed data. Current research focuses on improving the efficiency and accuracy of posterior sampling, particularly within the context of high-dimensional data and complex models, employing techniques like diffusion models, normalizing flows, and Langevin dynamics. These advancements are impacting diverse fields, including image processing, Bayesian inverse problems, and reinforcement learning, by enabling more robust and efficient inference in challenging scenarios. The development of computationally tractable algorithms for posterior sampling is crucial for advancing these areas.

Papers

October 16, 2023

Provable Probabilistic Imaging using Score-Based Generative Priors
Yu Sun, Zihui Wu, Yifan Chen, Berthy T. Feng, Katherine L. Bouman
Inverse Problem Image Reconstruction Score Based Generative Posterior Sampling Ill Posed Inverse Problem Bayesian Imaging

October 11, 2023

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
Reinforcement Learning Causal Graph Posterior Sampling Bayesian Regret Causal System

October 9, 2023

Optimal Exploration is no harder than Thompson Sampling
Zhaoqi Li, Kevin Jamieson, Lalit Jain
Thompson Sampling Posterior Sampling

October 5, 2023

October 4, 2023

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
Paul Hagemann, Johannes Hertrich, Fabian Altekrüger, Robert Beinert, Jannis Chemseddine, Gabriele Steidl
Gradient Flow Conditional Generative Posterior Sampling Maximum Mean Discrepancy Wasserstein Gradient Flow Negative Distance Kernel

September 27, 2023

Provably Efficient Exploration in Constrained Reinforcement Learning:Posterior Sampling Is All You Need
Danil Provodin, Pratik Gajane, Mykola Pechenizkiy, Maurits Kaptein
Efficient Exploration Posterior Sampling Constrained Reinforcement Learning Constrained Markov Decision Process Bayesian Regret

September 9, 2023

AmbientFlow: Invertible generative models from incomplete, noisy measurements
Varun A. Kelkar, Rucha Deshpande, Arindam Banerjee, Mark A. Anastasio
Generative Model Image Reconstruction Posterior Sampling Variational Bayesian Flow Based Generative Noisy Measurement Invertible Generative Model

July 11, 2023

Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling
Jack Jewson, Sahra Ghalebikesabi, Chris Holmes
Posterior Sampling Differential Privacy Guarantee Private Estimation Beta Divergence Private Bayesian

July 2, 2023

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models
Litu Rout, Negin Raoof, Giannis Daras, Constantine Caramanis, Alexandros G. Dimakis, Sanjay Shakkottai
Diffusion Model Super Resolution Latent Diffusion Model Posterior Sampling Ill Posed Inverse Problem Linear Inverse Problem Sample Reconstruction

June 12, 2023

Generative Plug and Play: Posterior Sampling for Inverse Problems
Charles A. Bouman, Gregery T. Buzzard
Inverse Problem Posterior Sampling Plug and Play Tomographic Reconstruction Play Style Sparse Approximation

June 7, 2023

Estimating Uncertainty in PET Image Reconstruction via Deep Posterior Sampling
Tin Vlašić, Tomislav Matulić, Damir Seršić
Uncertainty Estimation Posterior Sampling Positron Emission Tomography Bayesian Inversion

May 28, 2023

Conditional score-based diffusion models for Bayesian inference in infinite dimensions
Lorenzo Baldassari, Ali Siahkoohi, Josselin Garnier, Knut Solna, Maarten V. de Hoop
Inverse Problem Bayesian Inference Posterior Sampling Score Based Diffusion Model Linear Inverse Problem Infinite Dimensional

May 26, 2023

Accelerating Diffusion Models for Inverse Problems through Shortcut Sampling
Gongye Liu, Haoze Sun, Jiayi Li, Fei Yin, Yujiu Yang
Diffusion Model Zero Shot Inverse Problem Posterior Sampling Inversion Performance Sampling Technique

April 30, 2023

Posterior Sampling for Deep Reinforcement Learning
Remo Sasso, Michelangelo Conserva, Paulo Rauber
Reinforcement Learning Deep Reinforcement Learning Posterior Sampling

February 8, 2023

Learning How to Infer Partial MDPs for In-Context Adaptation and Exploration
Chentian Jiang, Nan Rosemary Ke, Hado van Hasselt
LeArning Abstract Markov Decision Process Environment Exploration Posterior Sampling Posterior Approximation Exploration Exploitation Contextual Adapter

February 6, 2023

Sampling-Based Accuracy Testing of Posterior Estimators for General Inference
Pablo Lemos, Adam Coogan, Yashar Hezaveh, Laurence Perreault-Levasseur
Posterior Inference Posterior Sampling Generative Factor Parameter Inference Accuracy Measurement

January 30, 2023

Reweighted Interacting Langevin Diffusions: an Accelerated Sampling Methodfor Optimization
Junlong Lyu, Zhitang Chen, Wenlong Lyu, Jianye Hao
Langevin Dynamic Posterior Sampling Particle System Sampling Based Optimization

January 27, 2023

Safe Posterior Sampling for Constrained MDPs with Bounded Constraint Violation
Krishna C Kalagarla, Rahul Jain, Pierluigi Nuzzo
Posterior Sampling Constrained Markov Decision Process Simple Regret Sequential Decision Making Constraint Violation

January 12, 2023

Thompson Sampling with Diffusion Generative Prior
Yu-Guan Hsieh, Shiva Prasad Kasiviswanathan, Branislav Kveton, Patrick Blöbaum
Diffusion Model Thompson Sampling Posterior Sampling Bandit Model Generative Diffusion Prior Bandit Task