Research map / Learning theory and algorithms / Sample complexity
Agnostic Multi-Group Active Learning
Nicholas Rittler, Kamalika Chaudhuri
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 per-group agnostic hypotheses to create artificial labels before multi-group ERM | Artificial-labeling approximation with A_DHM · Full agnostic multi-group learning | worst-case error guarantee: 2 \cdot \max_{g \in [G]} \nu_g + \epsilon; 3 \cdot L_{\mathcal{G}}^{\max}(h^*) + \epsilon | Mixed |
| Apply the group-realizable artificial-labeling reduction in the full agnostic regime | Group Realizable Algorithm · Full agnostic multi-group learning | consistency | Hurt |
Closest papers by meaning
- Simple and near-optimal algorithms for hidden stratification and multi-group learning (ICML 2022 · similarity 0.89)
- Multi-group Learning for Hierarchical Groups (ICML 2024 · similarity 0.88)
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.85)
- Active Generalized Category Discovery (CVPR 2024 · similarity 0.85)
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.85)
- Metric-Agnostic Continual Learning for Sustainable Group Fairness (AAAI 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.
