Scale-invariant Learning by Physics Inversion

被引:0
|
作者
Holl, Philipp [1 ]
Koltun, Vladlen [2 ]
Thuerey, Nils [1 ]
机构
[1] Tech Univ Munich, Munich, Germany
[2] Apple, Cupertino, CA USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse problems. We find that state-of-the-art training techniques are not well-suited to many problems that involve physical processes. The highly nonlinear behavior, common in physical processes, results in strongly varying gradients that lead first-order optimizers like SGD or Adam to compute suboptimal optimization directions. We propose a novel hybrid training approach that combines higher-order optimization methods with machine learning techniques. We take updates from a scale-invariant inverse problem solver and embed them into the gradient-descent-based learning pipeline, replacing the regular gradient of the physical process. We demonstrate the capabilities of our method on a variety of canonical physical systems, showing that it yields significant improvements on a wide range of optimization and learning problems.
引用
收藏
页数:14
相关论文
共 50 条
  • [1] Scale-invariant dynamical fluctuations in jet physics
    Chekanov, SV
    EUROPEAN PHYSICAL JOURNAL C, 1999, 6 (02): : 331 - 342
  • [2] Scale-invariant dynamical fluctuations in jet physics
    Chekanov S.V.
    The European Physical Journal C - Particles and Fields, 1999, 6 (2): : 331 - 342
  • [3] Scale-invariant representation of machine learning
    Lee, Sungyeop
    Jo, Junghyo
    PHYSICAL REVIEW E, 2022, 105 (04)
  • [4] Scale-Invariant Learning-to-Rank
    Petrozziello, Alessio
    Sommeregger, Christian
    Lim, Ye-Sheen
    PROCEEDINGS OF THE EIGHTEENTH ACM CONFERENCE ON RECOMMENDER SYSTEMS, RECSYS 2024, 2024, : 826 - 828
  • [5] Scale-invariant unconstrained online learning
    Kotlowski, Wojciech
    THEORETICAL COMPUTER SCIENCE, 2020, 808 : 139 - 158
  • [6] Scale-invariant learning and convolutional networks
    Chintala, Soumith
    Ranzato, Marc'Aurelio
    Szlam, Arthur
    Tian, Yuandong
    Tygert, Mark
    Zaremba, Wojciech
    APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS, 2017, 42 (01) : 154 - 166
  • [7] Object class recognition by unsupervised scale-invariant learning
    Fergus, R
    Perona, P
    Zisserman, A
    2003 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL II, PROCEEDINGS, 2003, : 264 - 271
  • [8] Scale-invariant inflation
    Rinaldi, M.
    Cecchini, C.
    Ghoshal, A.
    Mukherjee, D.
    AVENUES OF QUANTUM FIELD THEORY IN CURVED SPACETIME, AQFTCS 2022, 2023, 2531
  • [9] ON SCALE-INVARIANT DISTRIBUTIONS
    WHITTAKER, JV
    SIAM JOURNAL ON APPLIED MATHEMATICS, 1983, 43 (02) : 257 - 267
  • [10] Scale-invariant groups
    Nekrashevych, Volodymyr
    Pete, Gabor
    GROUPS GEOMETRY AND DYNAMICS, 2011, 5 (01) : 139 - 167