Infinite-width limit of deep linear neural networks

29 November 2022

Papers citing "Infinite-width limit of deep linear neural networks"

9 / 9 papers shown

Title
How Feature Learning Can Improve Neural Scaling Laws Blake Bordelon Alexander B. Atanasov Cengiz Pehlevan 70 14 0 26 Sep 2024
Gradient flows on graphons: existence, convergence, continuity equations Sewoong Oh Soumik Pal Raghav Somani Raghavendra Tripathi 27 5 0 18 Nov 2021
Implicit Bias of SGD for Diagonal Linear Networks: a Provable Benefit of Stochasticity Scott Pesme Loucas Pillaud-Vivien Nicolas Flammarion 39 100 0 17 Jun 2021
Towards a Mathematical Understanding of Neural Network-Based Machine Learning: what we know and what we don't E. Weinan Chao Ma Stephan Wojtowytsch Lei Wu AI4CE 61 134 0 22 Sep 2020
Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers B. Bah Holger Rauhut Ulrich Terstiege Michael Westdickenberg MLT 8 62 0 12 Oct 2019
Kernel and Rich Regimes in Overparametrized Models Blake E. Woodworth Suriya Gunasekar Pedro H. P. Savarese E. Moroshko Itay Golan Jason D. Lee Daniel Soudry Nathan Srebro 55 358 0 13 Jun 2019
Implicit Regularization in Deep Matrix Factorization Sanjeev Arora Nadav Cohen Wei Hu Yuping Luo AI4CE 61 500 0 31 May 2019
Width Provably Matters in Optimization for Deep Linear Neural Networks S. Du Wei Hu 53 94 0 24 Jan 2019
Gradient Descent Provably Optimizes Over-parameterized Neural Networks S. Du Xiyu Zhai Barnabás Póczós Aarti Singh MLT ODL 127 1,261 0 04 Oct 2018