Research map / Optimization / Implicit bias and generalization
Implicit Regularization in Deep Matrix Factorization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| increase depth of matrix factorization from 2 to 3 or 4 (ablation) | deep matrix factorization trained by gradient descent · low-rank matrix completion (100x100, rank 5 and 10) with few observed entries | reconstruction error | Helped |
| increase depth with many observed entries (ablation) | deep matrix factorization · low-rank matrix completion | reconstruction error | No clear effect |
| use gradient descent on matrix factorization instead of minimum nuclear norm solution | matrix completion with few observed entries · low-rank matrix completion | reconstruction error / effective rank | Helped |
| reduce initialization standard deviation (ablation) | depth-2 matrix factorization · matrix completion | effective rank | Helped |
| reduce initialization standard deviation (ablation) | depth-3 and depth-4 matrix factorization · matrix completion | reconstruction error | No clear effect |
| reduce learning rate (ablation) | matrix factorization · matrix completion | final reconstruction error | No clear effect |
Closest papers by meaning
- Implicit Regularization in Deep Learning May Not Be Explainable by Norms (NeurIPS 2020 · similarity 0.95)
- Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning (ICLR 2021 · similarity 0.94)
- Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent (ICML 2025 · similarity 0.91)
- Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion (NeurIPS 2024 · similarity 0.90)
- Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries (ICLR 2025 · similarity 0.90)
- Estimating Implicit Regularization in Deep Learning (NeurIPS 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.