Research map / Label-efficient and robust learning / Noisy labels
Convex and Non-Convex Approaches for Statistical Inference with Class-Conditional Noisy Labels
Hyebin Song, Ran Dai, Garvesh Raskutti, Rina Foygel Barber
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 the non-convex likelihood-based estimator instead of the convex surrogate estimator (larger subspace gap between design and perturbed design) | logistic regression with class-conditional noisy labels · simulated Gaussian mixture, n=1000, p=10 | relative efficiency (ratio of mean squared errors) | Improved |
| increase distance between the two Gaussian mixture means in the design (ablation) | convex surrogate estimator · simulated Gaussian mixture, n=1000, p=10 | subspace gap | Hurt |
| use the convex estimator instead of the likelihood-based estimator in sparse low-signal high-dimensional regimes | convex surrogate estimator · sparse high-dimensional simulation | mean squared error | Improved |
Closest papers by meaning
- Hypothesis Testing for Class-Conditional Noise Using Local Maximum Likelihood (AAAI 2024 · similarity 0.91)
- Learning from Noisy Labels via Conditional Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.87)
- SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning (ICML 2024 · similarity 0.86)
- Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design (NeurIPS 2026 · similarity 0.86)
- Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise (NeurIPS 2026 · similarity 0.85)
- Robust Logit Adjustment for Learning with Long-Tailed Noisy Data (AAAI 2025 · 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.
