Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Foolish Crowds Support Benign Overfitting
Niladri S. Chatterji, Philip Long
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 sparse interpolation (basis pursuit) instead of minimum-ℓ2-norm interpolation (OLS) | Interpolating linear regression · k = 5, p = n², ε = 1/n², σ² = ‖θ*‖₂² = 1 | excess risk: OLS: O\left(\frac{1}{n}\right); basis pursuit: Ω\left(\frac{1}{\log^2 n}\right) | Hurt |
| Use sparse interpolation (basis pursuit) instead of minimum-ℓ2-norm interpolation (OLS) | Interpolating linear regression · k = 5, p = n², ε = 1/n², σ² = ‖θ*‖₂² = log² n | excess risk: OLS: O\left(\frac{\log^2 n}{n}\right); basis pursuit: bounded below by a constant | Hurt |
| Constrain an interpolating predictor to have at most s nonzero parameters | Any interpolating procedure in the stated scenario · (k,p,n,ε,σ)-scenario | excess risk: \frac{c_3 \sigma^2 n}{s \log^2 (3p/s)} | Hurt |
Closest papers by meaning
- Avoiding Imposters and Delinquents: Adversarial Crowdsourcing and Peer Prediction (NeurIPS 2016 · similarity 0.76)
- CODEs: Chamfer Out-of-Distribution Examples Against Overconfidence Issue (ICCV 2021 · similarity 0.75)
- Making Better Use of the Crowd: How Crowdsourcing Can Advance Machine Learning Research (JMLR 2018 · similarity 0.75)
- Gaming Consensus: Coordinated Manipulation in Crowdsourced Fact-Checking (ICML 2026 · similarity 0.75)
- CrowdDiff: Multi-hypothesis Crowd Density Estimation using Diffusion Models (CVPR 2024 · similarity 0.74)
- Benign Overfitting in Single-Head Attention (NeurIPS 2025 · similarity 0.74)
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.
