Neural Networks Efficiently Learn Low-Dimensional Representations with
SGD

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

29 September 2022

Alireza Mousavi-Hosseini

Sejun Park

Ioannis Mitliagkas

Murat A. Erdogdu

Papers citing "Neural Networks Efficiently Learn Low-Dimensional Representations with SGD"

8 / 8 papers shown

Title
A Robust Monotonic Single-Index Model for Skewed and Heavy-Tailed Data: A Deep Neural Network Approach Applied to Periodontal Studies Qingyang Liu Shijie Wang Ray Bai Dipankar Bandyopadhyay OOD 18 0 0 04 May 2025
ReLU Neural Networks with Linear Layers are Biased Towards Single- and Multi-Index Models Suzanna Parkinson Greg Ongie Rebecca Willett 33 6 0 24 May 2023
Learning Single-Index Models with Shallow Neural Networks A. Bietti Joan Bruna Clayton Sanford M. Song 132 65 0 27 Oct 2022
$Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$-Covers$ Generalization Bounds for Stochastic Gradient Descent via Localized $\varepsilon$ -Covers Sejun Park Umut Simsekli Murat A. Erdogdu 31 9 0 19 Sep 2022
Convex Analysis of the Mean Field Langevin Dynamics Atsushi Nitanda Denny Wu Taiji Suzuki MLT 53 63 0 25 Jan 2022
Nonparametric Regression with Shallow Overparameterized Neural Networks Trained by GD with Early Stopping Ilja Kuzborskij Csaba Szepesvári 37 6 0 12 Jul 2021
A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network Mo Zhou Rong Ge Chi Jin 51 44 0 04 Feb 2021
Deep Networks and the Multiple Manifold Problem Sam Buchanan D. Gilboa John N. Wright 161 35 0 25 Aug 2020