Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
University of Manchester · Broad Institute · Microsoft Research Cambridge · University of Bristol · Inria · Duke University · KAUST · Helmholtz AI & TU Munich · University of Tuebingen · University of Cambridge · NMBU, University of Oslo, HiOF · ETH-Z, MPI-IS · Insitro · RIKEN · Vector Institute · Imperial College London · University of California, Irivine · Lancaster University · U Oxford · New York University · LMU Munich, MCML · Oxford and DeepMind · University of Amsterdam & Qualcomm · Purdue University
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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.