Research map / Label-efficient and robust learning / Recognition and long-tail
Strategic Classification with Unknown User Manipulations
Tosca Lechner, Ruth Urner, Shai Ben-David
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 |
|---|---|---|---|
| Learner estimates unknown manipulation graph from unlabeled manipulated samples in batch rounds (strategic batch-learning protocol) instead of knowing the graph | Strategic classification with thresholds and totally ordered graph classes · Theoretical (PAC-style sample and round complexity) | sample and round complexity for near-optimal strategic loss | Improved |
| Threshold algorithm in realizable case with robust realizability (one round, no manipulated samples) | Thresholds with fixed-radius manipulation graphs · Theoretical | round complexity | No clear effect |
| Improper learning via maximally robust ERM with ultrafilter extension of hypothesis class, instead of proper learning | Finite VC classes with totally ordered graph classes · Theoretical, realizable case | learnability (success for every true graph in G) | Improved |
Closest papers by meaning
- Strategic Classification With Externalities (ICLR 2025 · similarity 0.88)
- One-Shot Strategic Classification Under Unknown Costs (ICML 2024 · similarity 0.87)
- Strategic Classification with Non-Linear Classifiers (NeurIPS 2025 · similarity 0.87)
- Bayesian Strategic Classification (NeurIPS 2024 · similarity 0.87)
- Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification (NeurIPS 2024 · similarity 0.87)
- Should Decision-Makers Reveal Classifiers in Online Strategic Classification? (ICML 2025 · 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.
