Research map / Optimization / Implicit bias and generalization
Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing
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 |
|---|---|---|---|
| Use small initialization (alpha→0) for GD instead of large initialization (ablation) | GD on matrix sensing (over-parameterized) · Matrix sensing d=50, r*=5 | implicit low-rank bias (incremental learning of ranks) | Helped |
| Increase number of measurements m (reduce measurement error δ) (ablation) | GD with small initialization on matrix sensing · Matrix sensing d=50, r*=5 | relative error to X_s | Helped |
| Small initialization with exact parameterization (r=r*=5) (ablation) | GD on matrix sensing · Matrix sensing d=50, r*=5, m=1000 | convergence time | Hurt |
Closest papers by meaning
- Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing (NeurIPS 2023 · similarity 0.90)
- The Power of Preconditioning in Overparameterized Low-Rank Matrix Sensing (ICML 2023 · similarity 0.89)
- How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization (ICLR 2024 · similarity 0.89)
- Globally Q-linear Gauss-Newton Method for Overparameterized Non-convex Matrix Sensing (NeurIPS 2024 · similarity 0.86)
- SGD vs GD: Rank Deficiency in Linear Networks (NeurIPS 2024 · similarity 0.86)
- The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing (NeurIPS 2024 · similarity 0.86)
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.