Research map / Federated learning and privacy / Differential privacy
Multiclass versus Binary Differentially Private PAC Learning
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 |
|---|---|---|---|
| Reduce multiclass learning to learning its binary label-bit restrictions | Private PAC learning of a [k]-valued class · Multiclass private PAC learning | sample complexity upper bound: 2^{O(k^d)} -> O\Big(\frac{d^6 (\log(k+1))^8 \log^4(\frac{d \log^3(k+1)}{\epsilon \delta \alpha \beta})}{\epsilon \alpha} | Helped |
| Use binary learners with sample complexity polynomial in Littlestone dimension | Binary restrictions of the multiclass class · Multiclass private PAC learning | sample complexity upper bound: O\left(\frac{d_L^6 \log^2(\frac{d_L}{\alpha \beta \epsilon \delta})}{\epsilon \alpha^2}\right) -> O\Big(\frac{d^6 (\log( | Helped |
| Control binary restriction dimensions by the multiclass Littlestone dimension | A [k]-valued hypothesis class · Binary restrictions of a multiclass class | maximum Littlestone dimension: \max_{i=1, \dots, \log(k+1)} d_i \leq 6 d \ln(k+1) | Helped |
Closest papers by meaning
- An Õptimal Differentially Private PAC Learner for Concept Classes with VC Dimension 1 (NeurIPS 2026 · similarity 0.92)
- Oracle-Efficient Differentially Private Learning with Public Data (NeurIPS 2024 · similarity 0.86)
- Improved Sample Complexity for Multiclass PAC Learning (NeurIPS 2024 · similarity 0.85)
- On the Computational Landscape of Replicable Learning (NeurIPS 2024 · similarity 0.85)
- Fast Rates for Bandit PAC Multiclass Classification (NeurIPS 2024 · similarity 0.85)
- Computationally Efficient Replicable Learning of Parities and Applications (NeurIPS 2026 · 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.