Research map / Learning theory and algorithms / Sample complexity
On the Equivalence between Online and Private Learnability beyond Binary Classification
Young Jung, Baekjin Kim, Ambuj Tewari
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 |
|---|---|---|---|
| Assume private PAC learnability | Multi-class classification · Multi-class classification | online learnability | Improved |
| Assume private PAC learnability | Regression · Regression | online learnability | Improved |
| Use global stability as an intermediate step | Online-learnable multi-class classes · Multi-class classification | private learnability | Improved |
| Use tolerance-based Littlestone dimension and relaxed zero-one loss to connect discretized regression to multi-class learning | Regression classes · Regression | online learnability characterization | Improved |
| Require a finite class or finite input domain | Online-learnable regression classes · Regression | private learnability | Improved |
| Require a finite range over the input domain | Online-learnable regression classes · Regression | private learnability | Improved |
| Require finite sup-norm covers at every scale | Online-learnable regression classes · Regression | private learnability | Improved |
| Require finite sequential Pollard pseudo-dimension | Online-learnable regression classes · Regression | private learnability | Improved |
| Apply the global-stability and stable-histogram proof strategy directly to real-valued regression | Online-learnable regression classes · Regression | private learnability equivalence | No clear effect |
Closest papers by meaning
- Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings (NeurIPS 2025 · similarity 0.87)
- Smoothed Online Classification can be Harder than Batch Classification (NeurIPS 2024 · similarity 0.87)
- Computable universal online learning (NeurIPS 2025 · similarity 0.86)
- The Limits of Differential Privacy in Online Learning (NeurIPS 2024 · similarity 0.85)
- Oracle-Efficient Differentially Private Learning with Public Data (NeurIPS 2024 · similarity 0.85)
- A Trichotomy for List Transductive Online Learning (ICML 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.
