Research map / Learning theory and algorithms / Sample complexity
The Sample Complexity of Semi-Supervised Learning with Nonparametric Mixture Models
Chen Dan, Liu Leqi, Bryon Aragam, Pradeep K Ravikumar, Eric P Xing
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 density information (MLE) instead of majority vote (MV) to estimate the permutation | SSL permutation estimator · Synthetic and MNIST mixtures | recovery of true permutation: n = 20 vs n = 40 | Improved |
| misspecify the learned mixture (Lambda != Lambda*) and increase overlap | MLE estimator · Synthetic and MNIST mixtures | recovery of true permutation | Mixed |
| increase number of classes to K = 16 | MLE, Greedy, MV · Gaussian mixture | recovery of true permutation: 50% | Hurt |
| use the proposed SSL classifier instead of supervised LeNet with few labels | MNIST classifier · MNIST | classification accuracy: 96% | Improved |
Closest papers by meaning
- Can semi-supervised learning use all the data effectively? A lower bound perspective (NeurIPS 2023 · similarity 0.89)
- A Random Matrix Analysis and Improvement of Semi-Supervised Learning for Large Dimensional Data (JMLR 2018 · similarity 0.88)
- Nearly Optimal Sample Complexity for Learning with Label Proportions (ICML 2025 · similarity 0.87)
- Evaluating multiple models using labeled and unlabeled data (NeurIPS 2025 · similarity 0.87)
- Out-Of-Domain Unlabeled Data Improves Generalization (ICLR 2024 · similarity 0.86)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.86)
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.
