Overview

Bayesian inference combines prior beliefs with observed data to form a posterior distribution over unknown quantities, supporting predictions and decisions that account for uncertainty. Common approaches include Markov chain Monte Carlo, variational inference, Laplace approximations, and simulation-based inference; neural networks and normalizing flows increasingly help approximate or amortize these computations. Applications range from scientific inverse problems and time-series models to causal analysis, machine learning, and robotics. A central challenge is making inference scalable without losing posterior accuracy or calibrated uncertainty, especially when priors or likelihood models are misspecified.

Latest papers

CardsList

336 papers25 papers in the last four weeks, down 44% on the four weeks before. 0.2% of all new papers.

  1. Very fast Bayesian Additive Regression Trees on GPU

    Oct 30, 2024Giacomo PetrilloNonparametric RegressionGPU Acceleration

  2. Noise-Aware Differentially Private Variational Inference

    Oct 25, 2024Talal Alrawajfeh, Joonas Jälkö, Antti HonkelaBayesian InferenceDifferential Privacy

  3. Joint Bayesian Parameter and Model Order Estimation for Low-Rank Probability Mass Tensors

    Oct 8, 2024Joseph K. Chege, Arie Yeredor, Martin HaardtBayesian InferenceTensor Decomposition

  4. Hierarchical Bayesian Crowdsourcing with Item Difficulty

    May 29, 2024Seong Woo Han, Ozan Adıgüzel, Bob CarpenterInter-Rater ReliabilityLatent Variable Models

  5. PhyloGFN: Phylogenetic inference with generative flow networks

    Oct 12, 2023Mingyang Zhou, Zichao Yan, Elliot Layne +5Bayesian InferencePosterior Sampling

  6. A Bayesian Approach for the Network Reconstruction of Interdependent Critical Infrastructure Systems from Cascading Failures

    Nov 28, 2022MirSaleh Bahavarnia, Hiba Baroud, Yu Wang +1Bayesian Inference