Score: 1

Understanding Incremental Learning with Closed-form Solution to Gradient Flow on Overparamerterized Matrix Factorization

Published: August 28, 2025 | arXiv ID: 2508.20344v1

By: Hancheng Min, René Vidal

Potential Business Impact:

Teaches computers to learn things step-by-step.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

Many theoretical studies on neural networks attribute their excellent empirical performance to the implicit bias or regularization induced by first-order optimization algorithms when training networks under certain initialization assumptions. One example is the incremental learning phenomenon in gradient flow (GF) on an overparamerterized matrix factorization problem with small initialization: GF learns a target matrix by sequentially learning its singular values in decreasing order of magnitude over time. In this paper, we develop a quantitative understanding of this incremental learning behavior for GF on the symmetric matrix factorization problem, using its closed-form solution obtained by solving a Riccati-like matrix differential equation. We show that incremental learning emerges from some time-scale separation among dynamics corresponding to learning different components in the target matrix. By decreasing the initialization scale, these time-scale separations become more prominent, allowing one to find low-rank approximations of the target matrix. Lastly, we discuss the possible avenues for extending this analysis to asymmetric matrix factorization problems.

Country of Origin
🇺🇸 🇨🇳 United States, China

Page Count
6 pages

Category
Computer Science:
Machine Learning (CS)