Research map / Label-efficient and robust learning / Noisy labels
Online Strategic Classification With Noise and Partial Feedback
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Studies online strategic binary linear classification where agents manipulate features under costly effort, with noisy labels and only partial (post-decision) feedback available to the principal.
Problem
Online learning of a binary linear classifier from sequentially arriving strategic agents who manipulate features to obtain positive labels, when the principal does not know the true feature-label distribution and observes only partial, noisy feedback.
Approach
Studies the online strategic classification setting jointly with label noise and partial feedback, providing learning guarantees for the principal's linear classifier under these constraints (abstract truncated, so specific algorithmic details are not stated).
Closest papers by meaning
- Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification (NeurIPS 2024 · similarity 0.89)
- Bayesian Strategic Classification (NeurIPS 2024 · similarity 0.89)
- One-Shot Strategic Classification Under Unknown Costs (ICML 2024 · similarity 0.88)
- Strategic Classification With Externalities (ICLR 2025 · similarity 0.87)
- Strategic Classification with Non-Linear Classifiers (NeurIPS 2025 · similarity 0.87)
- Online Linear Classification with Massart Noise (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.