conftrace_

deep linear network

25 papers

Explore in graph

Co-occurring keywords

gradient descent (1144) gradient flow (142) representation learning (6206) implicit regularization (93) neural network optimization (1293) matrix factorization (529) learning dynamics (75) feature learning (1311) learning theory (519) saddle point (95)

Papers

Feature Learning in Finite-Width Bayesian Deep Linear Networks with Multiple Outputs and Convolutional Layers JMLR 2025
Efficient Low-Dimensional Compression of Overparameterized Models AISTATS 2024
Deep linear networks for regression are implicitly regularized towards flat minima NIPS 2024
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks? NIPS 2024
Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks NIPS 2024
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data ICML 2023
The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023
Critical Points and Convergence Analysis of Generative Deep Linear Networks Trained with Bures-Wasserstein Loss ICML 2023
Deep linear networks can benignly overfit when shallow ones do JMLR 2023
Exact learning dynamics of deep linear networks with prior knowledge NIPS 2022
Learning dynamics of deep linear networks with multiple pathways NIPS 2022
Combining Explicit and Implicit Regularization for Efficient Learning in Deep Networks NIPS 2022
On the Stability and Scalability of Node Perturbation Learning NIPS 2022
On Non-local Convergence Analysis of Deep Linear Networks ICML 2022
Exact Solutions of a Deep Linear Network NIPS 2022
Student-Teacher Learning From Clean Inputs to Noisy Inputs CVPR 2021
Analytic Insights into Structure and Rank of Neural Network Hessian Maps NIPS 2021
Why bigger is not always better: on finite and infinite neural networks ICML 2020
Implicit Bias in Deep Linear Classification: Initialization Scale vs Training Accuracy NIPS 2020
On Dropout and Nuclear Norm Regularization ICML 2019
Width Provably Matters in Optimization for Deep Linear Neural Networks ICML 2019
Implicit Regularization in Deep Matrix Factorization NIPS 2019
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks ICML 2018
Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global ICML 2018
Exact natural gradient in deep linear networks and its application to the nonlinear case NIPS 2018