Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft
Committee Machines

Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft Committee Machines

29 April 2021

Frederieke Richert

Roman Worschech

Papers citing "Soft Mode in the Dynamics of Over-realizable On-line Learning for Soft Committee Machines"

5 / 5 papers shown

Title
Toward Global Convergence of Gradient EM for Over-Parameterized Gaussian Mixture Models Weihang Xu Maryam Fazel Simon S. Du 41 1 0 29 Jun 2024
How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization Nuoya Xiong Lijun Ding Simon S. Du 37 11 0 03 Oct 2023
Online Learning for the Random Feature Model in the Student-Teacher Framework Roman Worschech B. Rosenow 46 0 0 24 Mar 2023
Over-Parameterization Exponentially Slows Down Gradient Descent for Learning a Single Neuron Weihang Xu S. Du 37 16 0 20 Feb 2023
Hidden Unit Specialization in Layered Neural Networks: ReLU vs. Sigmoidal Activation Elisa Oostwal Michiel Straat Michael Biehl MLT 56 54 0 16 Oct 2019