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

We provide an explicit analysis of the dynamics of vanilla gradient descent for deep matrix factorization in a setting where the minimizer of the loss function is unique. We show that the recovery rate of ground-truth eigenvectors is proportional to the magnitude of the corresponding eigenvalues and that the differences among the rates are amplified as the depth of the factorization increases. For exactly characterized time intervals, the effective rank of gradient descent iterates is provably close to the effective rank of a low-rank projection of the ground-truth matrix, such that early stopping of gradient descent produces regularized solutions that may be used for denoising, for instance. In particular, apart from few initial steps of the iterations, the effective rank of our matrix is monotonically increasing, suggesting that "matrix factorization implicitly enforces gradient descent to take a route in which the effective rank is monotone". Since empirical observations in more general scenarios such as matrix sensing show a similar phenomenon, we believe that our theoretical results shed some light on the still mysterious "implicit bias" of gradient descent in deep learning.

• 4 publications
• 1 publication
• 12 publications
• 17 publications
05/31/2019

Implicit Regularization in Deep Matrix Factorization

Efforts to understand the generalization mystery in deep learning have l...
11/17/2021

How and When Random Feedback Works: A Case Study of Low-Rank Matrix Factorization

The success of gradient descent in ML and especially for learning neural...
03/06/2022

Algorithmic Regularization in Model-free Overparametrized Asymmetric Matrix Factorization

We study the asymmetric matrix factorization problem under a natural non...
06/13/2017

Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations

Non-negative matrix factorization is a basic tool for decomposing data i...
02/13/2020

Fast Convergence for Langevin Diffusion with Matrix Manifold Structure

In this paper, we study the problem of sampling from distributions of th...
11/17/2019

Deep Matrix Factorization with Spectral Geometric Regularization

Deep Matrix Factorization (DMF) is an emerging approach to the problem o...
09/21/2022

A Validation Approach to Over-parameterized Matrix and Image Recovery

In this paper, we study the problem of recovering a low-rank matrix from...