Statistical Physics Meets Machine Learning II
FOCUS · T28 · ID: 2154366
Presentations
-
Scaling Laws and Emergent Behaviors in Foundation Models
ORAL · Invited
–
Presenters
-
Irina Rish
MILA
Authors
-
Irina Rish
MILA
-
-
Reliable emulation of complex functionals by active learning with error control
ORAL
–
Publication: Fang, X., Gu, M., & Wu, J. (2022). Reliable emulation of complex functionals by active learning with error control. The Journal of Chemical Physics, 157(21).
Presenters
-
Xinyi Fang
University of California, Santa Barbara
Authors
-
Xinyi Fang
University of California, Santa Barbara
-
Mengyang Gu
University of California, Santa Barbara
-
Jianzhong Wu
University of California, Riverside
-
-
Towards measuring generalization performance of deep neural networks via the Fisher information matrix
ORAL
–
Presenters
-
Chase W Goddard
Princeton University
Authors
-
Chase W Goddard
Princeton University
-
David J Schwab
The Graduate Center, CUNY
-
-
Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos
ORAL
–
Presenters
-
Dayal Singh Kalra
University of Maryland, College Park
Authors
-
Dayal Singh Kalra
University of Maryland, College Park
-
Tianyu He
University of Maryland, College Park
-
Maissam Barkeshli
University of Maryland, College Park
-
-
Statistical Mechanics of Semantic Compression
ORAL · Invited
–
Presenters
-
Tankut U Can
Institute for Advanced Study
Authors
-
Tankut U Can
Institute for Advanced Study
-
-
Bounds on learning with power-law priors
ORAL
–
Presenters
-
Sean A Ridout
Emory University
Authors
-
Sean A Ridout
Emory University
-
Ilya M Nemenman
Emory, Emory University
-
Ard A Louis
University of Oxford
-
Chris Mingard
University of Oxford
-
Radosław Grabarczyk
University of Oxford
-
Kamaludin Dingle
Gulf University for Science & Technology
-
Guillermo Valle Pérez
University of Oxford
-
Charles London
University of Oxford
-
-
In-depth analysis of the learning process for a small artificial neural network
ORAL
–
Publication: X. Yang, K. Arora, and M. Bachmann, "Dissecting a Small Artificial Neural Network", preprint (2023).
Presenters
-
Xiguang Yang
University of Georgia
Authors
-
Xiguang Yang
University of Georgia
-
Krish Arora
University of Georgia
-
Michael Bachmann
University of Georgia
-
-
Understanding Neural Network Generalizability from the Perspective of Entropy
ORAL
–
Publication: Preprint: Correlation between entropy and generalizability in a neural network
https://arxiv.org/abs/2207.01996Presenters
-
Entao Yang
Air Liquide
Authors
-
Entao Yang
Air Liquide
-
Xiaotian Zhang
City University of Hong Kong
-
Ge Zhang
City University of Hong Kong
-
-
Deep Variational Multivariate Information Bottleneck
ORAL
–
Publication: https://openreview.net/forum?id=ZhY1XSYqO4
https://arxiv.org/abs/2310.03311Presenters
-
K. Michael Martini
Emory University
Authors
-
K. Michael Martini
Emory University
-
Eslam Abdelaleem
Emory University
-
Ilya M Nemenman
Emory, Emory University
-
-
Nonlinear classification of neural manifolds with context information: geometrical properties and storage capacity
ORAL
–
Presenters
-
Francesca Mignacco
CUNY Graduate Center
Authors
-
Francesca Mignacco
CUNY Graduate Center
-
Chi-Ning Chou
Flatiron Institute
-
SueYeon Chung
New York University
-