Predicting the outputs of finite deep neural networks trained with noisy
gradients

Predicting the outputs of finite deep neural networks trained with noisy gradients

2 April 2020

Papers citing "Predicting the outputs of finite deep neural networks trained with noisy gradients"

11 / 11 papers shown

Title
Grokking as a First Order Phase Transition in Two Layer Networks Noa Rubin Inbar Seroussi Z. Ringel 37 15 0 05 Oct 2023
Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks Blake Bordelon Cengiz Pehlevan MLT 38 29 0 06 Apr 2023
Online Learning for the Random Feature Model in the Student-Teacher Framework Roman Worschech B. Rosenow 46 0 0 24 Mar 2023
Globally Gated Deep Linear Networks Qianyi Li H. Sompolinsky AI4CE 27 10 0 31 Oct 2022
Self-Consistent Dynamical Field Theory of Kernel Evolution in Wide Neural Networks Blake Bordelon Cengiz Pehlevan MLT 40 78 0 19 May 2022
Contrasting random and learned features in deep Bayesian linear regression Jacob A. Zavatone-Veth William L. Tong Cengiz Pehlevan BDL MLT 28 26 0 01 Mar 2022
Separation of Scales and a Thermodynamic Description of Feature Learning in Some CNNs Inbar Seroussi Gadi Naveh Z. Ringel 33 50 0 31 Dec 2021
Unified field theoretical approach to deep and recurrent neuronal networks Kai Segadlo Bastian Epping Alexander van Meegen David Dahmen Michael Krämer M. Helias AI4CE BDL 37 20 0 10 Dec 2021
The large learning rate phase of deep learning: the catapult mechanism Aitor Lewkowycz Yasaman Bahri Ethan Dyer Jascha Narain Sohl-Dickstein Guy Gur-Ari ODL 159 234 0 04 Mar 2020
Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime Stéphane dÁscoli Maria Refinetti Giulio Biroli Florent Krzakala 93 152 0 02 Mar 2020
MCMC using Hamiltonian dynamics Radford M. Neal 185 3,266 0 09 Jun 2012