Convergence and Implicit Bias of Gradient Flow on Overparametrized Linear Networks
read the original abstract
Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon is to study how initialization and overparametrization affect convergence and implicit bias of training algorithms. In this paper, we present a novel analysis of single-hidden-layer linear networks trained under gradient flow, which connects initialization, optimization, and overparametrization. Firstly, we show that the squared loss converges exponentially to its optimum at a rate that depends on the level of imbalance and the margin of the initialization. Secondly, we show that proper initialization constrains the dynamics of the network parameters to lie within an invariant set. In turn, minimizing the loss over this set leads to the min-norm solution. Finally, we show that large hidden layer width, together with (properly scaled) random initialization, ensures proximity to such an invariant set during training, allowing us to derive a novel non-asymptotic upper-bound on the distance between the trained network and the min-norm solution.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
A Theory of Saddle Escape in Deep Nonlinear Networks
Derives exact Frobenius norm imbalance identity for deep nonlinear networks, classifies activations into four classes, and obtains critical-depth escape time law τ★ = Θ(ε^{-(r-2)}) from reduction to scalar ODE on perm...
-
Estimating Implicit Regularization in Deep Learning
Gradient matching empirically recovers implicit regularization effects such as l2 penalties from early stopping and dropout in neural networks.
-
A Theory of Saddle Escape in Deep Nonlinear Networks
Derives exact norm-imbalance identity for deep nonlinear nets, classifying activations into four classes and yielding escape time law τ★ = Θ(ε^{-(r-2)}) governed by bottleneck depth r.
-
A Theory of Saddle Escape in Deep Nonlinear Networks
An exact norm-imbalance identity classifies activations into four classes and reduces deep nonlinear training flow to a scalar ODE that predicts saddle escape time scaling as ε to the power of minus (r-2) for r bottle...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.