Research map / Learning theory and algorithms / Sample complexity
Optimal Learners for Realizable Regression: PAC Learning and Online Learning
Idan Attias, Steve Hanneke, Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas
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 |
|---|---|---|---|
| Characterize realizable PAC learnability using the scaled OIG dimension | Real-valued hypothesis classes · Realizable PAC regression | PAC learnability | Improved |
| Use a deterministic learner guided by the online dimension | Real-valued hypothesis classes · Realizable online regression | expected cumulative loss: \mathfrak{C}_\infty \leq \mathbb{D}^\mathrm{onl}(\mathcal{H}) + \epsilon; lower bound: \mathfrak{C}_\infty \geq \mathbb{ | Improved |
| Characterize worst-case ERM learnability using the scaled Graph dimension | Real-valued hypothesis classes · Realizable PAC regression by any ERM | PAC learnability | Improved |
| Require finite scaled DS dimension as a necessary condition | Real-valued hypothesis classes · Realizable PAC regression | PAC learnability | Improved |
| Use finite fat-shattering dimension as a learnability criterion | Real-valued hypothesis classes · Realizable PAC regression | PAC learnability | No clear effect |
| Assume finite scaled DS dimension is sufficient for learnability | Real-valued hypothesis classes · Realizable PAC regression | PAC learnability | Mixed |
Closest papers by meaning
- Scale-Sensitive Shattering: Learnability and Evaluability at Optimal Scale (NeurIPS 2026 · similarity 0.87)
- Transductive Learning is Compact (NeurIPS 2024 · similarity 0.86)
- On the Computational Landscape of Replicable Learning (NeurIPS 2024 · similarity 0.86)
- Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models (NeurIPS 2025 · similarity 0.86)
- Smoothed Online Classification can be Harder than Batch Classification (NeurIPS 2024 · similarity 0.86)
- On Agnostic PAC Learning in the Small Error Regime (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.
