4 papers
Earthquake magnitudes depend on seismic history, as revealed by a neural network analysis
Neri Berman, Oleg Zlydenko, Oren Gilon +2
Earthquake occurrence is notoriously difficult to predict. While some aspects of their spatiotemporal statistics can be relatively well captured by point-process models, very littl…
The Implicit Bias of Logit Regularization
Alon Beck, Yohai Bar Sinai, Noam Levi
Logit regularization, the addition of a convex penalty directly in logit space, is widely used in modern classifiers, with label smoothing as a prominent example. While such method…
Machine Learning the Entropy to Estimate Free Energy Differences without Sampling Transitions
Yamin Ben-Shimon, Barak Hirshberg, Yohai Bar-Sinai
Thermodynamic phase transitions, a central concept in physics and chemistry, are typically controlled by an interplay of enthalpic and entropic contributions. In most cases, the es…
Grokking at the Edge of Linear Separability
Alon Beck, Noam Levi, Yohai Bar-Sinai
We investigate the phenomenon of grokking -- delayed generalization accompanied by non-monotonic test loss behavior -- in a simple binary logistic classification task, for which "m…