Statistical Physics Meets Machine Learning I

Presentations

• Grokking and emergent capabilities in deep learning

  ORAL · Invited

  March 7, 2024, 8:00 AM – March 7, 2024, 8:36 AM

  Publication: https://arxiv.org/pdf/2301.02679.pdf

  Presenters

  • Andrey Gromov

    • University of Maryland, College Park

  Authors

  • Andrey Gromov

    • University of Maryland, College Park

  View abstract →

• Average-Reward Reinforcement Learning Using Insights from Non-Equilibrium Statistical Mechanics

  ORAL

  March 7, 2024, 8:36 AM – March 7, 2024, 8:48 AM

  Publication: "Entropy regularized reinforcement learning using large deviation theory": Phys. Rev. Research 5, 023085
  "Bayesian inference approach for entropy regularized reinforcement learning with stochastic dynamics": PMLR 216:99-109, 2023

  Presenters

  • Jacob Adamczyk

    • University of Massachusetts Boston

  Authors

  • Jacob Adamczyk

    • University of Massachusetts Boston

  • Argenis Arriojas Maldonado

    • University of Massachusetts Boston

  • Stas Tiomkin

    • San Jose State University

  • Rahul V Kulkarni

    • University of Massachusetts Boston

  View abstract →

• To grok or not to grok: Disentangling generalization and memorization on corrupted algorithmic datasets

  ORAL

  March 7, 2024, 8:48 AM – March 7, 2024, 9:00 AM

  Presenters

  • Darshil H Doshi

    • University of Maryland, College Park

  Authors

  • Darshil H Doshi

    • University of Maryland, College Park

  • Aritra Das

    • University of Maryland College Park

  • Tianyu He

    • University of Maryland, College Park

  • Andrey Gromov

    • University of Maryland, College Park

  View abstract →

• Generalization error in the spherical perceptron

  ORAL

  March 7, 2024, 9:00 AM – March 7, 2024, 9:12 AM

  Presenters

  • Gilhan Kim

    • Seoul Natl Univ

  Authors

  • Gilhan Kim

    • Seoul Natl Univ

  • Yongjoo Baek

    • Seoul National University

  • Hyungjoon Soh

    • Seoul Natl Univ

  View abstract →

• Criticality from the functional development of a learning machine

  ORAL

  March 7, 2024, 9:12 AM – March 7, 2024, 9:24 AM

  Presenters

  • Ting-Kuo Lee

    • National Tsing Hua University

  Authors

  • Ting-Kuo Lee

    • National Tsing Hua University

  View abstract →

• Training Machine Learning Emulators to Preserve Invariant Measures of Chaotic Attractors

  ORAL · Invited

  March 7, 2024, 9:24 AM – March 7, 2024, 10:00 AM

  Publication: Accepted at NeurIPS 2023. (Preprint available: arXiv:2306.01187)
  R. Jiang, P. Y. Lu, E. Orlova, and R. Willett, Training Neural Operators to Preserve Invariant Measures of Chaotic Attractors. Advances in Neural Information Processing Systems, 2023.

  Presenters

  • Peter Y Lu

    • University of Chicago

  Authors

  • Peter Y Lu

    • University of Chicago

  • Ruoxi Jiang

    • University of Chicago

  • Elena Orlova

    • University of Chicago

  • Rebecca Willett

    • University of Chicago

  View abstract →

• Statistical mechanics of dynamical system identification

  ORAL

  March 7, 2024, 10:00 AM – March 7, 2024, 10:12 AM

  Publication: Statistical Mechanics of Dynamical System Identification, A. A. Klishin, J. Bakarji, J. N. Jutz, K. Manohar, in preparation

  Presenters

  • Andrei A Klishin

    • University of Washington

  Authors

  • Andrei A Klishin

    • University of Washington

  • Joseph Bakarji

    • University of Washington

  • J. Nathan Kutz

    • University of Washington, AI Institute for Dynamic Systems

  • Krithika Manohar

    • University of Washington

  View abstract →

• Effective Dynamics of Generative Adversarial Networks

  ORAL

  March 7, 2024, 10:12 AM – March 7, 2024, 10:24 AM

  Publication: S. Durr, Y. Mroueh, Y. Tu, and S. Wang. Effective dynamics of generative adversarial networks. Physical Review X 13, 041004 (2023).

  Presenters

  • Shenshen Wang

    • University of California, Los Angeles

  Authors

  • Shenshen Wang

    • University of California, Los Angeles

  • Steven Durr

    • University of California, Los Angeles

  • Youssef Mroueh

    • IBM T. J. Watson Research Center

  • Yuhai Tu

    • IBM T. J. Watson Research Center

  View abstract →

• Machine Learning that predicts well may not learn the correct physical descriptions of glassy systems.

  ORAL

  March 7, 2024, 10:24 AM – March 7, 2024, 10:36 AM

  Presenters

  • Arabind Swain

    • Emory University

  Authors

  • Arabind Swain

    • Emory University

  • Sean A Ridout

    • Emory University

  • Ilya M Nemenman

    • Emory
    • Emory University

  View abstract →

• Tracking parameter variations in nonlinear dynamical systems using machine learning

  ORAL

  March 7, 2024, 10:36 AM – March 7, 2024, 10:48 AM

  Publication: Z.-M. Zhai, M. Moradi, M. Haile, and Y.-C. Lai, Tracking parameter variations in nonlinear dynamical systems using machine learning, planned papers (2023).

  Presenters

  • Zheng-Meng Zhai

    • Arizona state university

  Authors

  • Zheng-Meng Zhai

    • Arizona state university

  • Mohammadamin Moradi

    • Arizona State University

  • Ying-Cheng Lai

    • Arizona State University

  View abstract →

• Sparse spectra in learned representations of symmetries

  ORAL

  March 7, 2024, 10:48 AM – March 7, 2024, 11:00 AM

  Presenters

  • Michael C Abbott

    • Yale University

  Authors

  • Michael C Abbott

    • Yale University

  • Benjamin B Machta

    • Yale University

  View abstract →