Implicit Regularization in Deep Matrix Factorization

by   Sanjeev Arora, et al.

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit regularization of gradient descent over deep linear neural networks for matrix completion and sensing --- a model referred to as deep matrix factorization. Our first finding, supported by theory and experiments, is that adding depth to a matrix factorization enhances an implicit tendency towards low-rank solutions, oftentimes leading to more accurate recovery. Secondly, we present theoretical and empirical arguments questioning a nascent view by which implicit regularization in matrix factorization can be captured using simple mathematical norms. Our results point to the possibility that the language of standard regularizers may not be rich enough to fully encompass the implicit regularization brought forth by gradient-based optimization.


page 1

page 2

page 3

page 4


Implicit Regularization in Deep Learning May Not Be Explainable by Norms

Mathematically characterizing the implicit regularization induced by gra...

On implicit regularization: Morse functions and applications to matrix factorization

In this paper, we revisit implicit regularization from the ground up usi...

Gradient Descent for Deep Matrix Factorization: Dynamics and Implicit Bias towards Low Rank

We provide an explicit analysis of the dynamics of vanilla gradient desc...

Deep Matrix Factorization with Spectral Geometric Regularization

Deep Matrix Factorization (DMF) is an emerging approach to the problem o...

Implicit Regularization in Tensor Factorization

Implicit regularization in deep learning is perceived as a tendency of g...

In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning

We present experiments demonstrating that some other form of capacity co...

AIR-Net: Adaptive and Implicit Regularization Neural Network for Matrix Completion

Conventionally, the matrix completion (MC) model aims to recover a matri...