conftrace_

linear network

17 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) neural network (6616) implicit bia (107) neural network optimization (1293) lazy training (13) schatten norm (15) learning dynamics (75) implicit regularization (93) convolutional neural network (4226) convergence rate (607)

Papers

SGD vs GD: Rank Deficiency in Linear Networks NIPS 2024
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning NIPS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes NIPS 2024
Linear Convergence of Gradient Descent For Finite Width Over-parametrized Linear Networks With General Initialization AISTATS 2023
What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models NIPS 2023
Linear CNNs Discover the Statistical Structure of the Dataset Using Only the Most Dominant Frequencies ICML 2023
(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability NIPS 2023
Implicit Bias of Linear Equivariant Networks ICML 2022
Implicit Bias of the Step Size in Linear Diagonal Neural Networks ICML 2022
A Modular Analysis of Provable Acceleration via Polyak’s Momentum: Training a Wide ReLU Network and a Deep Linear Network ICML 2021
A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer ALT 2021
On the Explicit Role of Initialization on the Convergence and Implicit Bias of Overparametrized Linear Networks ICML 2021
Training Linear Neural Networks: Non-Local Convergence and Complexity Results ICML 2020
Implicit Rank-Minimizing Autoencoder NIPS 2020
Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks NIPS 2019
The Dynamics of Learning: A Random Matrix Approach ICML 2018