Performative Prediction

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

Performative Prediction with Selective Labels
Oct 6, 2026Giovani Valdrighi, Isabel Valera, Marcos Medeiros RaimundoPerformative Prediction Selective Labels
Instituto de Computação Universidade Estadual de Campinas Campinas, Brazil · Department of Computer Science Saarland University Saarbrücken, Germany
Performative Privacy: When Differential Privacy Maximizes Utility
Aug 28, 2026Uddalak Mukherjee, Edwige Cyffers, Yann ChevaleyreData Leakage Differential Privacy
Dauphine PSL · CNRS Dauphine PSL
The Role of Causality in Algorithmic Recourse
Jul 30, 2026Srikanth Avasarala, Varun Gupta, Shahin Jabbari +2Performative Prediction Algorithmic Recourse
Georgia Institute of Technology · Vector Institute · Drexel University +1
Actions Have Consequences: Detecting Outcome Performativity using Intervention Testing
Jul 29, 2026Brandon Gower-Winter, Georg KremplPerformative Prediction
Utrecht University 8 Hiedelberglaan, Utrecht, 3584 CS, NL
Adaptive Gradient-Based Methods for a Broader Class of Optimization Problems under Performative Prediction
Jul 29, 2026Hiroki Hamaguchi, Yuya Hikima, Hiroshi Sawada +1Stochastic Optimization Convergence Adaptive Gradient Methods
Graduate School of Information Science and Technology, The University of Tokyo · Department of Industrial Engineering and Economics, Institute of Science Tokyo · Communication Science Laboratories, NTT, Inc. +1
Retraining Seeks Stable Signals
Jul 17, 2026Moritz HardtPerformative Prediction Statistical Learning Theory
Max Planck Institute for Intelligent Systems, Tübingen, and Tübingen AI Center
Unbiased Canonical Set-Valued Oracles Via Lattice Theory
Jun 24, 2026Jobst HeitzigPerformative Prediction
PIK-Potsdam
Federated Bilevel Performative Prediction
Jun 18, 2026Liangxin Qian, Chang Liu, Xuanyu Cao +2Bilevel Optimization Performative Prediction
College of Computing and Data Science, Nanyang Technological University, 639798, Singapore · Innovation and Management Center, School of Software Technology (Ningbo), Zhejiang University, 315100, China · School of Electrical Engineering & Computer Science, Washington State University, Pullman, WA 99164, USA.
Partially Performative Prediction
Jun 5, 2026Jaewook Lee, Tijana ZrnicDistribution Shift Performative Prediction
Department of Electrical Engineering, Stanford University · Departments of Statistics and Management Science & Engineering, Stanford University
Off-Policy Evaluation with Strategic Agents via Local Disclosure
Jun 5, 2026Kiet Q. H. Vo, Abbavaram Gowtham Reddy, Julian Rodemann +2Strategic Classification Off-Policy Evaluation
Rational Intelligence Lab, CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Relational Machine Learning Lab, CISPA Helmholtz Center for Information Security, Saarbrücken, Germany · Department of Statistics, LMU Munich, Germany +1
COPF: An Online Framework for Deployment-Stable Counterfactual Fairness in Evolving Graphs
May 30, 2026Sheng'en Li, Dongmian ZouAlgorithmic Fairness Counterfactual Fairness
Zu Chongzhi Center and DIRC, Duke Kunshan University, Kunshan, China.
Algometrics: Forecasting Under Algorithmic Feedback
May 13, 2026Marc SchmittTime Series Forecasting Performative Prediction
University of Oxford

Oct 6, 2026, cs.LGJ/K move · Enter open · S save

Performative Prediction with Selective Labels

Giovani Valdrighi, Isabel Valera, Marcos Medeiros Raimundo

Instituto de Computação Universidade Estadual de Campinas Campinas, Brazil · Department of Computer Science Saarland University Saarbrücken, Germany

Performative Prediction Selective Labels

Open paper AskPDF arXiv

Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distribution map that relates each model to the population distribution it induces. One of the main results in this framework showed that repeated risk minimization (RRM), which updates models by retraining on the most recent data, can converge to a stable model that minimizes risk on its own induced distribution. However, existing analyses typically assume access to the complete distributions of features and labels after model deployment, ignoring the possibility of selective labels: observing labels only for the accepted subset of the population. In this work, we formalize performative prediction with selective labels and show that retraining only on observed data can misguide the retraining procedure and undermine the guarantees of convergence to a stable solution. We then propose a worst-case objective based on knowledge of a confidence interval on the probability of a positive label. Applying RRM to this objective permits us to remain within a bounded distance to the true stable point. Under a sensitivity assumption on the conditional label distribution, we further show how previously accepted data can tighten these confidence intervals over time. Experiments in a lending application with fairness regularization show that our robust optimization approach closely matches the performance of RRM with complete label access.

Momentum

Related topics

Latest papers 12