Memorizing Gaussians with no over-parameterizaion via gradient decent on neural networks

28 March 2020

Papers citing "Memorizing Gaussians with no over-parameterizaion via gradient decent on neural networks"

5 / 5 papers shown

Title
Mixture of Parrots: Experts improve memorization more than reasoning Samy Jelassi Clara Mohri David Brandfonbrener Alex Gu Nikhil Vyas Nikhil Anand David Alvarez-Melis Yuanzhi Li Sham Kakade Eran Malach MoE 36 4 0 24 Oct 2024
Analysis of the expected $L_2$ error of an over-parametrized deep neural network estimate learned by gradient descent without regularization Selina Drews Michael Kohler 38 3 0 24 Nov 2023
Sharp Lower Bounds on Interpolation by Deep ReLU Neural Networks at Irregularly Spaced Data Jonathan W. Siegel 14 2 0 02 Feb 2023
The Interpolation Phase Transition in Neural Networks: Memorization and Generalization under Lazy Training Andrea Montanari Yiqiao Zhong 49 95 0 25 Jul 2020
Training (Overparametrized) Neural Networks in Near-Linear Time Jan van den Brand Binghui Peng Zhao Song Omri Weinstein ODL 29 82 0 20 Jun 2020