paper-with-me

Papers

A Complete Loss Landscape Analysis of Regularized Deep Matrix Factorization

2025-06-25 · Po Chen, Rujun Jiang, Peng Wang

Despite its wide range of applications across various domains, the optimization foundations of deep matrix factorization (DMF) remain largely open. In this work, we aim to fill this gap by conducting a comprehensive study of the loss landscape of the regularized DMF problem. Toward this goal, we first provide a closed-form expression of all critical points. Building on this, we establish precise conditions under which a critical point is a local minimizer, a global minimizer, a strict saddle point, or a non-strict saddle point. Leveraging these results, we derive a necessary and sufficient condition under which each critical point is either a local minimizer or a strict saddle point. This provides insights into why gradient-based methods almost always converge to a local minimizer of the regularized DMF problem. Finally, we conduct numerical experiments to visualize its loss landscape under different settings to support our theory.

📄 PDF Abstract BibTeX arXiv:2506.20344

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the Loss Landscape Geometry of Regularized Deep Matrix Factorization: Uniqueness and Sharpness

2026-03-28 · Anil Kamber, Rahul Parhi arxiv

Weight decay is ubiquitous in training deep neural network architectures. Its empirical success is often attributed to capacity control; nonetheless, our theoretical understanding of its effect on the loss landscape and …

Nonconvex Factorization and Manifold Formulations are Almost Equivalent in Low-rank Matrix Optimization

2021-08-03 · Yuetian Luo, Xudong Li, Anru R. Zhang

In this paper, we consider the geometric landscape connection of the widely studied manifold and factorization formulations in low-rank positive semidefinite (PSD) and general matrix optimization. We establish a sandwich…

RelationRetrieval

Error Bound Analysis for the Regularized Loss of Deep Linear Neural Networks

2025-02-16 · Po Chen, Rujun Jiang, Peng Wang

The optimization foundations of deep linear networks have received significant attention lately. However, due to the non-convexity and hierarchical structure, analyzing the regularized loss of deep linear networks remain…

CR-SAM: Curvature Regularized Sharpness-Aware Minimization

2023-12-21 · Tao Wu, Tie Luo, Donald C. Wunsch

The capacity to generalize to future unseen data stands as one of the utmost crucial attributes of deep neural networks. Sharpness-Aware Minimization (SAM) aims to enhance the generalizability by minimizing worst-case lo…

Feature-metric Loss for Self-supervised Learning of Depth and Egomotion

2020-07-21 · ECCV 2020 8 · Chang Shu, Kun Yu, Zhixiang Duan, Kuiyuan Yang

Photometric loss is widely used for self-supervised depth and egomotion estimation. However, the loss landscapes induced by photometric differences are often problematic for optimization, caused by plateau landscapes for…

Depth EstimationMonocular Depth EstimationSelf-Supervised LearningVisual Odometry