Bayesian Neural

Bayesian neural networks (BNNs) aim to combine the power of neural networks with the principled uncertainty quantification offered by Bayesian methods. Current research focuses on improving the scalability and efficiency of BNN training and inference, often employing techniques like sparse Bayesian learning, implicit models, and novel architectures such as recurrent neural networks and neural fields. These advancements are enabling the application of BNNs to increasingly complex problems in diverse fields, including cognitive science, medical image analysis, and speech recognition, where robust uncertainty estimates are crucial for reliable decision-making.

Papers

October 29, 2024

Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Vu C. Dinh, Lam Si Tung Ho, Cuong V. Nguyen
Hamiltonian Monte Carlo ReLU Neural Network Layer ReLU Network Novel Single Integrator Bayesian Neural

June 20, 2024

Latent Variable Sequence Identification for Cognitive Models with Neural Bayes Estimation
Ti-Fen Pan, Jing-Jing Li, Bill Thompson, Anne Collins
Latent Variable Cognitive Model Temporal Latent Bayesian Neural Latent Sequence

June 11, 2024

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis
Zeinab Abboud, Herve Lombaert, Samuel Kadoury
Uncertainty Quantification Medical Image Analysis Bayesian Neural Network Bayesian Perspective Predictive Uncertainty Posterior Approximation Bayesian Neural

May 30, 2024

The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Derek Lim, Theo Moe Putterman, Robin Walters, Haggai Maron, Stefanie Jegelka
Neural Network Parameter Lack Thereof Bayesian Neural Parameter Symmetry

May 26, 2024

Bayesian Inference with Deep Weakly Nonlinear Networks
Boris Hanin, Alexander Zlokapa
Bayesian Inference Deep Linear Bayesian Neural

March 12, 2024

Scalable Spatiotemporal Prediction with Bayesian Neural Fields
Feras Saad, Jacob Burnim, Colin Carroll, Brian Patton, Urs Köster, Rif A. Saurous, Matthew Hoffman
Spatio tempOral Spatiotemporal Prediction Spatiotemporal Datasets Bayes Net Bayesian Neural

December 6, 2023

nbi: the Astronomer's Package for Neural Posterior Estimation
Keming Zhang, Joshua S. Bloom, Stéfan van der Walt, Nina Hernitschek
Scientific Inference Astronomical Data Probabilistic Surrogate SPR Package Neural Posterior Estimation Cosmological Inference Bayesian Neural

July 31, 2023

A theory of data variability in Neural Network Bayesian inference
Javed Lindner, David Dahmen, Michael Krämer, Moritz Helias
Theoretical Understanding Kernel Method Generalization Property Kernel Matrix Non Pathological Variability Neural Network Gaussian Process Bayesian Neural

October 24, 2022

MARS: Meta-Learning as Score Matching in the Function Space
Krunoslav Lehman Pavasovic, Jonas Rothfuss, Andreas Krause
Meta Learning Prior Knowledge Score Matching Function Space Bayesian Neural Meta Learning Prior

September 6, 2022

Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distribution
Joel Janek Dabrowski, Daniel Edward Pagendam
Variational Inference Bayesian Neural Network Posterior Inference Posterior Approximation Implicit Model Posterior Predictive Approximate Bayesian Inference Bayesian Neural

February 17, 2022

Mitigating Closed-model Adversarial Examples with Bayesian Neural Modeling for Enhanced End-to-End Speech Recognition
Chao-Han Huck Yang, Zeeshan Ahmed, Yile Gu, Joseph Szurley, Roger Ren, Linda Liu, Andreas Stolcke, Ivan Bulyko
Adversarial Example End to End Adversarial Noise Textual Adversarial Example Bayesian Neural