The reviewed record of science sign in
Pith

arxiv: 2402.00809 · v5 · pith:C2HFGXCX · submitted 2024-02-01 · cs.LG · stat.ML

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

Theodore Papamarkou , Maria Skoularidou , Konstantina Palla , Laurence Aitchison , Julyan Arbel , David Dunson , Maurizio Filippone , Vincent Fortuin
show 17 more authors
Philipp Hennig Jos\'e Miguel Hern\'andez-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David R\"ugamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang
This is my paper

Reviewed by Pithpith:C2HFGXCXopen to challenge →

classification cs.LG stat.ML
keywords learningdeepbayesiandatalarge-scaleresearchtasksaccuracy
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Monte Carlo Stochastic Depth for Uncertainty Estimation in Deep Learning

    cs.LG 2026-04 unverdicted novelty 5.0

    Monte Carlo Stochastic Depth provides a theoretically linked and empirically competitive method for uncertainty quantification in modern deep learning models such as object detectors.

  2. Scalable Bayesian Spatial Mixture Modelling for Remote Sensing Image Segmentation

    stat.ME 2026-06 unverdicted novelty 4.0

    POTTERS extends the Potts model with generalized spatial dependence and external priors for Bayesian remote sensing image segmentation via variational inference, without needing target-region labels.

  3. Uncertainty in Physics and AI: Taxonomy, Quantification, and Validation

    stat.ML 2026-05 accept novelty 4.0

    A unified taxonomy of uncertainty in ML for physics is introduced together with validation tools such as coverage, calibration, and proper scoring rules, illustrated on regression and classification tasks.