Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics
cs.LG
Submitted: 2026-02-11
Updated: 2026-10-03
Comments: 9 pages, 4 figures, ICML 2026
Code: https://github.com/alkarmilina/multi-levelstrategic-classification
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On classification of strategic agents who can both game and improve
- Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
- The Role of Randomness and Noise in Strategic Classification
- Reinforcement Learning with Depreciating Assets
- Strategic Classification from Revealed Preferences
- Selective Classification for Deep Neural Networks
- Maximizing Welfare with Incentive-Aware Evaluation Mechanisms
- Strategic Classification
- Sequential Strategic Classification with Multi-Stage Selective Classifiers
- Addressing Polarization and Unfairness in Performative Prediction
- How Do Classifiers Induce Agents To Invest Effort Strategically?
- Strategic Classification is Causal Modeling in Disguise
- Performative Prediction
- Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
- Who Leads and Who Follows in Strategic Classification?
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks