Machine learning in context of physical systems merits a re-examination of the learning strategy. In addition to data, one can leverage a vast library of physical prior models (e.g. kinematics, fluid flow, etc) to perform more robust inference. The nascent sub-field of \emph{physics-based learning} (PBL) studies the blending of neural networks with physical priors. While previous PBL algorithms have been applied successfully to specific tasks, it is hard to generalize existing PBL methods to a wide range of physics-based problems. Such generalization would require an architecture that can adapt to variations in the correctness of the physics, or in the quality of training data. No such architecture exists. In this paper, we aim to generalize PBL, by making a first attempt to bring neural architecture search (NAS) to the realm of PBL. We introduce a new method known as physics-based neural architecture search (PhysicsNAS) that is a top-performer across a diverse range of quality in the physical model and the dataset.
Improving Neural Symbolic Regression with a Diverse Prior and Post-training Alignment
University of Freiburg(弗赖堡大学);LMU Munich(慕尼黑大学);Munich Center for Machine Learning (MCML)(慕尼黑机器学习中心);LAION;ELLIS Institute Tübingen(埃利斯研究所蒂宾根分部);Prior Labs
Institute of Systems and Robotics, University of Coimbra(科英布拉大学系统与机器人研究所);Institute of Pure and Applied Mathematics(纯数学与应用数学研究所);Tecgraf, Pontifical Catholic University of Rio de Janeiro(里约热内卢天主教大学Tecgraf研究所);Portuguese Mint and Official Printing Office(葡萄牙铸币与官方印刷局)
IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation
Zhejiang University of Technology(浙江工业大学);Shandong University(山东大学);Zhejiang Key Laboratory of Visual Information Intelligent Processing(浙江省可视信息智能处理重点实验室)
Unsupervised Behavior Extraction via Random Intent Priors
Institute for Interdisciplinary Information Sciences, Tsinghua University(清华大学交叉信息研究院);Department of Automation, Tsinghua University(清华大学自动化系);Department of Computer Science & Engineering, Washington University in St. Louis(圣路易斯华盛顿大学计算机科学与工程系)
Diverse super-resolution with pretrained deep hiererarchical VAEs
Univ. Bordeaux(波尔多大学);Bordeaux IMB(波尔多数学研究所);INP(国立波尔多综合理工学院);CNRS(法国国家科学研究中心);Ubisoft La Forge(育碧La Forge);Université Paris Cité(巴黎西岱大学);MAP5(MAP5实验室);INRIA(法国国家信息与自动化研究所)