Posterior Predictive

Posterior predictive distributions, representing the probability of future observations given observed data and a model, are central to Bayesian inference, aiming to quantify uncertainty and improve prediction accuracy. Current research focuses on improving the efficiency and accuracy of posterior predictive estimation, particularly within neural network architectures like neural processes and transformers, and addressing challenges like calibration, model misspecification, and computational cost in high-dimensional settings. These advancements are crucial for reliable uncertainty quantification in diverse applications, ranging from medical image analysis and personalized medicine to robust federated learning and efficient Bayesian optimization.

Papers

November 5, 2024

Proxy-informed Bayesian transfer learning with unknown sources
Sabina J. Sloman, Julien Martinelli, Samuel Kaski
Strong Generalization Transfer Learning Posterior Predictive Bayesian Transfer

October 8, 2024

Temperature Optimization for Bayesian Deep Learning
Kenyon Ng, Chris van der Heide, Liam Hodgkinson, Susan Wei
Bayesian Deep Learning Thermal Management Posterior Predictive Critical Temperature Cold Posterior Predictive Density

June 18, 2024

Translation Equivariant Transformer Neural Processes
Matthew Ashman, Cristiana Diaconu, Junhyuck Kim, Lakee Sivaraya, Stratis Markou, James Requeima, Wessel P. Bruinsma, Richard E. Turner
Neural Process Posterior Predictive Equivariant Machine Learning

June 13, 2024

Generative vs. Discriminative modeling under the lens of uncertainty quantification
Elouan Argouarc'h, François Desbouvries, Eric Barat, Eiji Kawasaki
Uncertainty Quantification Generative Question Camera Lens Marginal Distribution Prior Distribution Discriminative Model Posterior Predictive Inference Problem

May 30, 2024

Understanding and mitigating difficulties in posterior predictive evaluation
Abhinav Agrawal, Justin Domke
Technical Challenge Human Understanding Monte Carlo Posterior Predictive Optimization Proxy Approximate Bayesian Inference

March 26, 2024

Goal-Oriented Bayesian Optimal Experimental Design for Nonlinear Models using Markov Chain Monte Carlo
Shijie Zhong, Wanggang Shen, Tommie Catanach, Xun Huan
Bayesian Optimization Markov Chain Monte Carlo Nonlinear Model Experimental Design Posterior Sampling Posterior Predictive Optimal Experimental Design

March 16, 2024

Interpretable Machine Learning for TabPFN
David Rundel, Julius Kobialka, Constantin von Crailsheim, Matthias Feurer, Thomas Nagler, David Rügamer
Interpretable Machine Learning Posterior Predictive Prior Data Fitted Network

March 8, 2024

Bayesian Hierarchical Probabilistic Forecasting of Intraday Electricity Prices
Daniel Nickelsen, Gernot Müller
Probabilistic Forecast Forecast Utterance Posterior Predictive Electricity Price Forecasting

February 13, 2024

Gradient-flow adaptive importance sampling for Bayesian leave one out cross-validation with application to sigmoidal classification models
Joshua C Chang, Xiangting Li, Shixin Xu, Hao-Ren Yao, Julia Porcino, Carson Chow
Adaptive Importance Gradient Flow Hessian Matrix Bayesian Perspective Monte Carlo Cross Validation Posterior Predictive Model Generalizability Sigmoid Function

December 15, 2023

Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space
Mohsin Hasan, Guojun Zhang, Kaiyang Guo, Xi Chen, Pascal Poupart
Bayesian Inference Posterior Predictive Global Posterior

October 31, 2023

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks
Steven Adriaensen, Herilalaina Rakotoarison, Samuel Müller, Frank Hutter
Model Performance Extrapolation Framework Posterior Predictive Approximate Bayesian Inference Trend Extrapolation Prior Data Fitted Network Right Censored

October 26, 2023

Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
Konstantin Hess, Valentyn Melnychuk, Dennis Frauen, Stefan Feuerriegel
Differential Equation Treatment Effect Posterior Predictive Neural Stochastic Differential Equation Novel Bayesian

October 20, 2023

Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability
Maciej Falkiewicz, Naoya Takeishi, Imahn Shekhzadeh, Antoine Wehenkel, Arnaud Delaunoy, Gilles Louppe, Alexandros Kalousis
Bayesian Inference Posterior Inference Simulation Based Inference Posterior Predictive Neural Network Calibration Coverage Probability

October 2, 2023

If there is no underfitting, there is no Cold Posterior Effect
Yijie Zhang, Yi-Shan Wu, Luis A. Ortega, Andrés R. Masegosa
Posterior Inference Bayesian Perspective Model Overfitting Posterior Predictive Cold Posterior

September 25, 2023

Pseudo Label Selection is a Decision Problem
Julian Rodemann
Semi Supervised Learning Posterior Predictive Pseudo Labeled Data Decision Problem Pseudo Label Selection

August 26, 2023

A transport approach to sequential simulation-based inference
Paul-Baptiste Rubio, Youssef Marzouk, Matthew Parno
Surrogate Model Parameter Estimation Mobility Management Posterior Predictive Forward Model Sequential Bayesian Inference Sequential Inference

July 14, 2023

Variational Prediction
Alexander A. Alemi, Ben Poole
Bayesian Inference Posterior Predictive Predictive Distribution Variational Approximation Variational Density

June 7, 2023

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective
Yves Rychener, Daniel Kuhn, Tobias Sutter
End to End Stochastic Optimization Bayesian Perspective Posterior Predictive End to End Learning Robust Optimization Problem

June 6, 2023

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression
Youngsoo Baek, Samuel I. Berchuck, Sayan Mukherjee
Posterior Predictive Asymptotic Behavior Bayesian Uncertainty Random Feature Regression Bayesian Model Averaging Posteriori Error

May 27, 2023

PFNs4BO: In-Context Learning for Bayesian Optimization
Samuel Müller, Matthias Feurer, Noah Hollmann, Frank Hutter
Bayesian Optimization Bayesian Neural Network Surrogate Modeling Different Context Posterior Predictive Prior Data Fitted Network