Research map / Optimization / Implicit bias and generalization
The Landscape of Non-convex Empirical Risk with Degenerate Population Risk
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 the number of samples from M=3 to M=10 | Rank-1 matrix sensing · Rank-1 matrix sensing | correspondence between empirical and population local minima: M=3 -> M=10 | Helped |
| Increase the number of samples from M=3 to M=10 | Phase retrieval · Phase retrieval | correspondence between empirical and population local minima: M=3 -> M=10 | Helped |
| Increase the number of measurements | General-rank matrix sensing · General-rank matrix sensing (k=2, r=3, N=8) | distance between empirical and population local minima | Helped |
| Increase the number of samples, up to M=1000 | Rank-1 matrix sensing and phase retrieval · Rank-1 matrix sensing and phase retrieval | one-to-one correspondence between empirical and population saddle points: M=1000 | No clear effect |
Closest papers by meaning
- Differentially Private Empirical Risk Minimization with Smooth Non-Convex Loss Functions: A Non-Stationary View (AAAI 2019 · similarity 0.88)
- Characterization of Excess Risk for Locally Strongly Convex Population Risk (NeurIPS 2022 · similarity 0.87)
- On the Local Minima of the Empirical Risk (NeurIPS 2018 · similarity 0.86)
- Generalization and Robustness of the Tilted Empirical Risk (ICML 2025 · similarity 0.86)
- Differentially Private Empirical Risk Minimization with Non-convex Loss Functions (ICML 2019 · similarity 0.86)
- On the Asymptotic Distribution of the Minimum Empirical Risk (ICML 2024 · similarity 0.85)
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.