223 citations · 1.8k across the 31 of their papers we have counts for
31 papers
Grokking modular arithmetic
Andrey Gromov
We present a simple neural network that can learn modular arithmetic tasks and exhibits a sudden jump in generalization known as ``grokking''. Concretely, we present (i) fully-conn…
Signatures of Supersymmetry in the Fractional Quantum Hall Effect
Songyang Pu, Ajit C. Balram, Mikael Fremling +2
The Moore-Read state, one of the leading candidates for describing the fractional quantum Hall effect at filling factor , is a paradigmatic -wave superconductor with no…
Supergravity model of the Haldane-Rezayi fractional quantum Hall state
Dung Xuan Nguyen, Kartik Prabhu, Ajit C. Balram +1
Supersymmetry and supergravity were invented in the 1970s to solve fundamental problems in high-energy physics. Even though neither of these ideas has yet been confirmed in high-en…
Fracton Matter
Andrey Gromov, Leo Radzihovsky
We review a burgeoning field of "fractons" -- a class of models where quasi-particles are strictly immobile or display restricted mobility that can be understood through generalize…
AutoInit: Automatic Initialization via Jacobian Tuning
Tianyu He, Darshil Doshi, Andrey Gromov
Good initialization is essential for training Deep Neural Networks (DNNs). Oftentimes such initialization is found through a trial and error approach, which has to be applied anew…
Critical Initialization of Wide and Deep Neural Networks through Partial Jacobians: General Theory and Applications
Darshil Doshi, Tianyu He, Andrey Gromov
Deep neural networks are notorious for defying theoretical treatment. However, when the number of parameters in each layer tends to infinity, the network function is a Gaussian pro…