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

Download

• Paper
• arXiv

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.

Citation

Papamarkou, T., Skoularidou, M., Palla, K., Aitchison, L., Arbel, J., Dunson, D., Filippone, M., Fortuin, V., Hennin, P., Hubin, A., Immer, A., Karaletsos, T.,Khan, M. E., Kristiadi, A., Li, Y., Hernandez-Lobato, J., M., Mandt, S., Nemeth, C., Osborne, M. A., Rudner, T.G.J., Rugmer, D,. Teh, Y.W., Welling, M., Wilson, A.G. and Zhang, R. (2024). Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI. In Forty-first International Conference on Machine Learning.

@inproceedings{papamarkou2024position,
  title={Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI},
  author={Papamarkou, Theodore and Skoularidou, Maria and Palla, Konstantina and Aitchison, Laurence and Arbel, Julyan and Dunson, David and Filippone, Maurizio and Fortuin, Vincent and Hennig, Philipp and Hern{\'a}ndez-Lobato, Jos{\'e} Miguel and others},
  booktitle={Forty-first International Conference on Machine Learning},
  year={2024}
}