paper-with-me

홈 › Papers

Convergence of gradient descent for learning linear neural networks

2021-08-04 · Gabin Maxime Nguegnang, Holger Rauhut, Ulrich Terstiege

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on the step sizes gradient descent converges to a critical point of the loss function, i.e., the square loss in this article. Furthermore, we demonstrate that for almost all initializations gradient descent converges to a global minimum in the case of two layers. In the case of three or more layers we show that gradient descent converges to a global minimum on the manifold matrices of some fixed rank, where the rank cannot be determined a priori.

📄 PDF Abstract BibTeX arXiv:2108.02040

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Linear Convergence of Generalized Mirror Descent with Time-Dependent Mirrors

2020-09-18 · Adityanarayanan Radhakrishnan, Mikhail Belkin, Caroline Uhler

The Polyak-Lojasiewicz (PL) inequality is a sufficient condition for establishing linear convergence of gradient descent, even in non-convex settings. While several recent works use a PL-based analysis to establish linea…

Exact Linear Convergence Rate Analysis for Low-Rank Symmetric Matrix Completion via Gradient Descent

2021-02-04 · Trung Vu, Raviv Raich

Factorization-based gradient descent is a scalable and efficient algorithm for solving low-rank matrix completion. Recent progress in structured non-convex optimization has offered global convergence guarantees for gradi…

Low-Rank Matrix CompletionMatrix Completion

A Methodology Establishing Linear Convergence of Adaptive Gradient Methods under PL Inequality

2024-07-17 · Kushal Chakrabarti, Mayank Baranwal

Adaptive gradient-descent optimizers are the standard choice for training neural network models. Despite their faster convergence than gradient-descent and remarkable performance in practice, the adaptive optimizers are …

Iterative Pre-Conditioning for Expediting the Gradient-Descent Method: The Distributed Linear Least-Squares Problem

2020-08-06 · Kushal Chakrabarti, Nirupam Gupta, Nikhil Chopra

This paper considers the multi-agent linear least-squares problem in a server-agent network. In this problem, the system comprises multiple agents, each having a set of local data points, that are connected to a server. …

Global Convergence Analysis of Vanilla Gradient Descent for Asymmetric Matrix Completion

2025-08-13 · Xu Zhang, Shuo Chen, Jinsheng Li, Xiangying Pang 외 arxiv

This paper investigates the asymmetric low-rank matrix completion problem, which can be formulated as an unconstrained non-convex optimization problem with a nonlinear least-squares objective function, and is solved via …