_version_ 1866914902077079552
author Papamarkou, Theodore
Skoularidou, Maria
Palla, Konstantina
Aitchison, Laurence
Arbel, Julyan
Dunson, David
Filippone, Maurizio
Fortuin, Vincent
Hennig, Philipp
Hernández-Lobato, José Miguel
Hubin, Aliaksandr
Immer, Alexander
Karaletsos, Theofanis
Khan, Mohammad Emtiyaz
Kristiadi, Agustinus
Li, Yingzhen
Mandt, Stephan
Nemeth, Christopher
Osborne, Michael A.
Rudner, Tim G. J.
Rügamer, David
Teh, Yee Whye
Welling, Max
Wilson, Andrew Gordon
Zhang, Ruqi
author_facet Papamarkou, Theodore
Skoularidou, Maria
Palla, Konstantina
Aitchison, Laurence
Arbel, Julyan
Dunson, David
Filippone, Maurizio
Fortuin, Vincent
Hennig, Philipp
Hernández-Lobato, José Miguel
Hubin, Aliaksandr
Immer, Alexander
Karaletsos, Theofanis
Khan, Mohammad Emtiyaz
Kristiadi, Agustinus
Li, Yingzhen
Mandt, Stephan
Nemeth, Christopher
Osborne, Michael A.
Rudner, Tim G. J.
Rügamer, David
Teh, Yee Whye
Welling, Max
Wilson, Andrew Gordon
Zhang, Ruqi
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00809
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
Papamarkou, Theodore
Skoularidou, Maria
Palla, Konstantina
Aitchison, Laurence
Arbel, Julyan
Dunson, David
Filippone, Maurizio
Fortuin, Vincent
Hennig, Philipp
Hernández-Lobato, José Miguel
Hubin, Aliaksandr
Immer, Alexander
Karaletsos, Theofanis
Khan, Mohammad Emtiyaz
Kristiadi, Agustinus
Li, Yingzhen
Mandt, Stephan
Nemeth, Christopher
Osborne, Michael A.
Rudner, Tim G. J.
Rügamer, David
Teh, Yee Whye
Welling, Max
Wilson, Andrew Gordon
Zhang, Ruqi
Machine Learning
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.
title Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
topic Machine Learning
url https://arxiv.org/abs/2402.00809