arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00809cs.LGstat.ML
收藏

立场论文:在大规模 AI 时代需要贝叶斯深度学习

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

The University of Manchester(曼彻斯特大学);Broad Institute of MIT and Harvard(麻省理工学院与哈佛大学博德研究所);Spotify(Spotify公司);University of Bristol(布里斯托尔大学);Centre Inria de l’Université Grenoble Alpes(格勒诺布尔阿尔卑斯大学法国国家信息与自动化研究所中心);Duke University(杜克大学);KAUST(阿卜杜拉国王科技大学);Helmholtz AI(亥姆霍兹人工智能研究所);Technical University of Munich(慕尼黑工业大学);Munich Center for Machine Learning(慕尼黑机器学习中心);University of Tübingen(蒂宾根大学);University of Cambridge(剑桥大学);University of Oslo(奥斯陆大学);Norwegian University of Life Sciences(挪威生命科学大学);ETH Zurich(苏黎世联邦理工学院);Chan Zuckerberg Initiative(陈·扎克伯格倡议);RIKEN(理化学研究所)
Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, … 展开作者

Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, José Miguel Hernández-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 Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang

AI总结:

本文论证贝叶斯深度学习能弥补大规模 AI 对不确定性、主动与持续学习及科学数据等问题的忽视,并展望其与基础模型结合的研究方向。

摘要:

在当前深度学习研究格局中,主流重点是在涉及大型图像和语言数据集的监督任务中取得高预测准确率。然而,更广阔的视角揭示出许多被忽视的指标、任务和数据类型,例如不确定性、主动学习与持续学习,以及科学数据,它们都需要关注。贝叶斯深度学习(Bayesian deep learning,BDL)构成了一条很有前景的途径,能在这些多样场景中提供优势。本文主张 BDL 可以提升深度学习的能力。文中重新审视了 BDL 的优势,承认现有挑战,并重点介绍了一些旨在克服这些障碍的令人振奋的研究方向。展望未来,讨论聚焦于将大规模基础模型与 BDL 相结合、以释放其全部潜力的可行方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑