Research map / Learning theory and algorithms / Sample complexity
Tight Bounds for Collaborative PAC Learning via Multiplicative Weights
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 |
|---|---|---|---|
| Use multiplicative weights to adaptively allocate samples across player distributions instead of the grouping strategy | MWeights vs. CenLearn · Magic-1, Magic-2, Wine, Eye, Letter | sample complexity | Helped |
| Use multiplicative weights rather than uniform sampling from the pooled distribution | MWeights vs. Naive · Magic-1 and Magic-2 | sample complexity | Helped |
| Use uniform sampling from the pooled distribution rather than adaptive allocation | Naive · Magic-Even | sample complexity | Helped |
| Use multiplicative weights rather than the Blum et al. approach | MWeights vs. CenLearn · Real-world datasets (reported across Magic-1 through Letter) | sample complexity | Helped |
| Use the Blum et al. approach rather than uniform sampling | CenLearn vs. Naive · Real-world datasets | sample complexity | Mixed |
Closest papers by meaning
- Collaborative Learning with Different Labeling Functions (ICML 2024 · similarity 0.91)
- Learning Distributions from Multiple Data Providers (NeurIPS 2026 · similarity 0.86)
- Fast Rates for Bandit PAC Multiclass Classification (NeurIPS 2024 · similarity 0.86)
- Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale (NeurIPS 2026 · similarity 0.85)
- On the Computational Landscape of Replicable Learning (NeurIPS 2024 · similarity 0.85)
- Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models (NeurIPS 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.