Agustinus Kristiadi

Sriram Ganapathi Subramanian

Felix Strieth-Kalthoff

Vincent Fortuin

Pascal Poupart

Geoff Pleiss

CoRR, 2024

Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI.

[BibT_eX]

[DOI]

CoRR, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Structured Inverse-Free Natural Gradient Descent: Memory-Efficient & Numerically-Stable KFAC.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?

[BibT_eX]

[DOI]

Felix Strieth-Kalthoff

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Low-Cost Bayesian Methods for Fixing Neural Networks' Overconfidence

[BibT_eX]

[DOI]

PhD thesis, 2023

Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets.

[BibT_eX]

[DOI]

CoRR, 2023

On the Disconnect Between Theory and Practice of Overparametrized Neural Networks.

[BibT_eX]

[DOI]

Jonathan Wenger

Felix Dangel

CoRR, 2023

Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization.

[BibT_eX]

[DOI]

CoRR, 2023

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization.

[BibT_eX]

[DOI]

Felix Dangel

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Fast predictive uncertainty for classification with Bayesian deep networks.

[BibT_eX]

[DOI]

Marius Hobbhahn

Proceedings of the Uncertainty in Artificial Intelligence, 2022

Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks.

[BibT_eX]

[DOI]

Runa Eschenhagen

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Being a Bit Frequentist Improves Bayesian Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2021

Learnable uncertainty under Laplace approximations.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Laplace Redux - Effortless Bayesian Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features.

[BibT_eX]

[DOI]

CoRR, 2020

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks.

[BibT_eX]

[DOI]

Proceedings of the 37th International Conference on Machine Learning, 2020

2019

Predictive Uncertainty Quantification with Compound Density Networks.

[BibT_eX]

[DOI]