Bayesian Deep Learning

Bayesian deep learning aims to combine the power of deep neural networks with the principled uncertainty quantification offered by Bayesian methods. Current research focuses on improving the scalability and accuracy of Bayesian inference in deep networks, exploring various architectures like deep Gaussian processes and employing algorithms such as variational inference, Laplace approximations, and Hamiltonian Monte Carlo. This field is significant because it addresses the limitations of traditional deep learning by providing well-calibrated uncertainty estimates, crucial for safety-critical applications and improving the reliability of predictions in diverse fields like healthcare, finance, and scientific modeling. The development of efficient and accurate Bayesian deep learning methods is driving progress in trustworthy AI.

Papers

November 12, 2024

Bayesian Deep Learning Approach for Real-time Lane-based Arrival Curve Reconstruction at Intersection using License Plate Recognition Data
Yang He, Chengchuan An, Jiawei Lu, Yao-Jan Wu, Zhenbo Lu, Jingxin Xia
Full State Reconstruction Intersection Scenario Bayesian Deep Learning Arrival Estimation Traffic State Sequence

November 11, 2024

Predicting Country Instability Using Bayesian Deep Learning and Random Forest
Adam Zebrowski, Haithem Afli
Core Stability Bayesian Deep Learning Forest Environment Random Participation Uncertainty Prediction Global Scale Global Information

October 31, 2024

Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA
David Smerkous, Qinxun Bai, Fuxin Li
Deep Network Bayesian Deep Learning Diversity Enhancement Similarity Metric HyperSpherical Energy Kernel Trick

October 22, 2024

Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections
Marco Miani, Hrittik Roy, Søren Hauberg
Generative Model Vision Transformer Model Overfitting Bayesian Deep Learning Projection Bias Posterior Approximation Bayes Rule

October 20, 2024

On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees
Yijie Zhang
Bayesian Inference Bayesian Approach PAC Bayesian Bayesian Deep Learning Generalization Guarantee Bayesian Model Probabilistic Neural Network Cold Posterior

October 11, 2024

A Bayesian Approach to Weakly-supervised Laparoscopic Image Segmentation
Zhou Zheng, Yuichiro Hayashi, Masahiro Oda, Takayuki Kitasaka, Kensaku Mori
Segmentation Model Bayesian Approach Bayesian Deep Learning Cardiac Segmentation Sparse Annotation Surgical Video Segmentation

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

October 2, 2024

Deep Kernel Posterior Learning under Infinite Variance Prior Weights
Jorge Loría, Anindya Bhadra
Shallow Neural Network Bayesian Deep Learning Deep Kernel Learning Unbounded Variance Covariance Kernel

July 24, 2024

Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference
Jian Xu, Delu Zeng, John Paisley
Diffusion Model Variational Inference Many Sparse Posterior Inference Exceptional Point Bayesian Deep Learning Deep Gaussian Process

July 18, 2024

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
Tristan Cinquin, Marvin Pförtner, Vincent Fortuin, Philipp Hennig, Robert Bamler
Inductive Bias Bayesian Deep Learning Gaussian Prior Laplace Approximation Functional Prior Laplace fPINNs

July 2, 2024

The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networks
Mohammed Fellaji, Frédéric Pennerath
Bayesian Neural Network Epistemic Uncertainty Bayesian Deep Learning Proper Issue Labeling Epistemic Uncertainty Quantification

May 22, 2024

Generalized Laplace Approximation
Yinsong Chen, Samson S. Yu, Zhong Li, Chee Peng Lim
Bayesian Deep Learning Laplace Approximation

March 28, 2024

Improving Cancer Imaging Diagnosis with Bayesian Networks and Deep Learning: A Bayesian Deep Learning Approach
Pei Xi, Lin
Deep Learning Machine Learning Bayesian Network Bayesian Deep Learning Tumor Cell Bayesian Deep

March 22, 2024

Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Models
John Fischer, Marko Orescanin, Justin Loomis, Patrick McClure
Application Proficiency Variational Inference Bayesian Deep Learning Bayesian Model Modern Deep Learning Mean Aggregation Bayesian Federated Learning

March 15, 2024

Hessian-Free Laplace in Bayesian Deep Learning
James McInerney, Nathan Kallus
Hessian Matrix Bayesian Deep Learning Hessian Free

February 27, 2024

Prediction of the SYM-H Index Using a Bayesian Deep Learning Method with Uncertainty Quantification
Yasser Abduallah, Khalid A. Alobaid, Jason T. L. Wang, Haimin Wang, Vania K. Jordanova, Vasyl Yurchyshyn, Huseyin Cavus, Ju Jing
Human Prediction Uncertainty Quantification Bayesian Deep Learning Solar Wind Symptom H Index

February 12, 2024

Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing
Wei Xu, An Liu, Yiting Zhang, Vincent Lau
Model Compression Bayesian Deep Learning Approximate Message Bayesian Deep Global Posterior Sparse Bayesian

February 2, 2024

Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent
Luca Della Libera, Jacopo Andreoli, Davide Dalle Pezze, Mirco Ravanelli, Gian Antonio Susto
Variational Inference Bayesian Neural Network Bayesian Deep Learning Useful Life Stein Variational Gradient Descent

February 1, 2024

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A. Osborne, Tim G. J. Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang
Deep Learning Continual LEArning Speech Based Age Predictive Performance Product Specific Position Information Bayesian Deep Learning

January 30, 2024

Forecasting VIX using Bayesian Deep Learning
Héctor J. Hortúa, Andrés Mora-Valencia
Temporal Convolutional Network Bayesian Deep Learning Volatility Forecasting Modern Neural Network Probabilistic Deep Learning Volatility Index

Bayesian Deep Learning

Papers

Bayesian Deep Learning Approach for Real-time Lane-based Arrival Curve Reconstruction at Intersection using License Plate Recognition Data

Predicting Country Instability Using Bayesian Deep Learning and Random Forest

Enhancing Diversity in Bayesian Deep Learning via Hyperspherical Energy Minimization of CKA

Bayes without Underfitting: Fully Correlated Deep Learning Posteriors via Alternating Projections

On Cold Posteriors of Probabilistic Neural Networks: Understanding the Cold Posterior Effect and A New Way to Learn Cold Posteriors with Tight Generalization Guarantees

A Bayesian Approach to Weakly-supervised Laparoscopic Image Segmentation

Temperature Optimization for Bayesian Deep Learning

Deep Kernel Posterior Learning under Infinite Variance Prior Weights

Sparse Inducing Points in Deep Gaussian Processes: Enhancing Modeling with Denoising Diffusion Variational Inference

FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning

The Epistemic Uncertainty Hole: an issue of Bayesian Neural Networks

Generalized Laplace Approximation

Improving Cancer Imaging Diagnosis with Bayesian Networks and Deep Learning: A Bayesian Deep Learning Approach

Federated Bayesian Deep Learning: The Application of Statistical Aggregation Methods to Bayesian Models

Hessian-Free Laplace in Bayesian Deep Learning

Prediction of the SYM-H Index Using a Bayesian Deep Learning Method with Uncertainty Quantification

Bayesian Deep Learning Via Expectation Maximization and Turbo Deep Approximate Message Passing

Bayesian Deep Learning for Remaining Useful Life Estimation via Stein Variational Gradient Descent

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

Forecasting VIX using Bayesian Deep Learning