Statistical Physics Meets Machine Learning
INVITED · MAR-G54 · ID: 2764221
Presentations
-
A kinetic theory for the transition from memorization to in-context generalization
ORAL · Invited
–
Presenters
-
Gautam Reddy
Princeton University
Authors
-
Gautam Reddy
Princeton University
-
-
Computing with Neural Manifolds: Towards a Multi-Scale Understanding of Biological and Artificial Neural Networks
ORAL · Invited
–
Presenters
-
SueYeon Chung
Flatiron Institute / NYU
Authors
-
SueYeon Chung
Flatiron Institute / NYU
-
-
Probing the Latent Hierarchical Structure of Data via Diffusion Models
ORAL · Invited
–
Publication: Probing the Latent Hierarchical Structure of Data via Diffusion Models<br>Antonio Sclocchi, Alessandro Favero, Noam Itzhak Levi, Matthieu Wyart<br>arXiv preprint arXiv:2410.13770<br><br>A phase transition in diffusion models reveals the hierarchical nature of data<br>A Sclocchi, A Favero, M Wyart<br>arXiv preprint arXiv:2402.16991 (to appear in PNAS)
Presenters
-
Matthieu Wyart
Johns Hopkins University
Authors
-
Matthieu Wyart
Johns Hopkins University
-
-
Statistical physics insights into optimal training strategies
ORAL · Invited
–
Presenters
-
Francesca Mignacco
The Graduate Center, City University of New York
Authors
-
Francesca Mignacco
The Graduate Center, City University of New York
-
-
The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions
ORAL · Invited
–
Presenters
-
Andrew Saxe
University College London
Authors
-
Andrew Saxe
University College London
-