Research map / Learning theory and algorithms / Sample complexity
Learning Functional Distributions with Private Labels
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 |
|---|---|---|---|
| Add noisy label kernel K_eta (label randomization) with noise level eta < (M-1)/M and known eta to the predictor | Noisy Smooth Bayesian Predictor for finite hypothesis classes · finite F, adversarial features (singleton distributions S) | expected KL-risk (theoretical upper bound) | Mixed |
| Bounded-away-from-zero probabilities (delta_min) instead of adversarial near-zero probabilities | Finite hypothesis class predictor (no smoothing, K_eta^{-1} of Bayesian average) · finite F with p(x)[y] >= delta_min | expected KL-risk (theoretical upper bound) | Helped |
| Noise kernel K_eta applied to labels (noisy labels) relative to noiseless setting | Learning functional distributions · finite F, adversarial features | expected KL-risk growth rate | Hurt |
Closest papers by meaning
- Information-theoretic Limits of Online Classification with Noisy Labels (NeurIPS 2024 · similarity 0.89)
- Label Noise: Ignorance Is Bliss (NeurIPS 2024 · similarity 0.86)
- Learning from Noisy Labels via Conditional Distributionally Robust Optimization (NeurIPS 2024 · similarity 0.85)
- Public-data Assisted Private Stochastic Optimization: Power and Limitations (NeurIPS 2024 · similarity 0.85)
- The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination (NeurIPS 2025 · similarity 0.85)
- Exactly Minimax-Optimal Locally Differentially Private Sampling (NeurIPS 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.