Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
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.
Cite
@article{arxiv.2402.00809,
title = {Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI},
author = {Theodore Papamarkou and Maria Skoularidou and Konstantina Palla and Laurence Aitchison and Julyan Arbel and David Dunson and Maurizio Filippone and Vincent Fortuin and Philipp Hennig and José Miguel Hernández-Lobato and Aliaksandr Hubin and Alexander Immer and Theofanis Karaletsos and Mohammad Emtiyaz Khan and Agustinus Kristiadi and Yingzhen Li and Stephan Mandt and Christopher Nemeth and Michael A. Osborne and Tim G. J. Rudner and David Rügamer and Yee Whye Teh and Max Welling and Andrew Gordon Wilson and Ruqi Zhang},
journal= {arXiv preprint arXiv:2402.00809},
year = {2024}
}
Comments
Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria. PMLR 235, 2024