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

MCML Authors

Vincent Fortuin

Dr.

Associate

Bayesian Deep Learning

David Rügamer

Prof. Dr.

Principal Investigator

Statistics, Data Science and Machine Learning

Abstract

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

inproceedings

---

ICML 2024

41st International Conference on Machine Learning. Vienna, Austria, Jul 21-27, 2024.

---

Authors

T. Papamarkou • M. Skoularidou • K. Palla • L. Aitchison • J. Arbel • D. Dunson • M. Filippone • V. Fortuin • P. Hennig • J. M. Hernández-Lobato • A. Hubin • A. Immer • T. Karaletsos • M. E. Khan • A. Kristiadi • Y. Li • S. Mandt • C. Nemeth • M. A. Osborne • T. G. J. Rudner • D. Rügamer • Y. W. Teh • M. Welling • A. G. Wilson • R. Zhang

---

Links

URL

---

In Collaboration

---

Research Area

 A1 | Statistical Foundations & Explainability