Research map / Optimization / Optimizers
Easy Learning from Label Proportions
Robert Istvan Busa-Fekete, Heejin Choi, Travis Dick, Claudio Gentile, Andres Munoz medina
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 Easy-LLP instead of MeanMap | linear models · MNIST and CIFAR-10 binarizations | test accuracy | No clear effect |
| use Label generation baseline instead of Easy-LLP / MeanMap | linear models · MNIST and CIFAR-10 binarizations | test accuracy | Hurt |
| use Easy-LLP with neural network base models instead of other LLP methods | CNN / deep network · MNIST and CIFAR-10 binarizations | test accuracy | Improved |
| compare Easy-LLP against DA method | neural network · MNIST and CIFAR-10 | test accuracy | Mixed |
| train for more epochs with fixed bags | all LLP algorithms · MNIST and CIFAR-10 | test accuracy | Hurt |
| use bag-estimated unbiased loss in place of instance-level loss | Easy-LLP with CNN · MNIST even-vs-odd, bag size 32 | training loss estimate | Improved |
Closest papers by meaning
- Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions (CVPR 2025 · similarity 0.93)
- Rethinking Learning from Label Proportions via Moment Matching (NeurIPS 2026 · similarity 0.92)
- Nearly Optimal Sample Complexity for Learning with Label Proportions (ICML 2025 · similarity 0.91)
- Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation (ICLR 2024 · similarity 0.91)
- Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical (ICML 2024 · similarity 0.87)
- Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss (NeurIPS 2024 · similarity 0.87)
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.
