Performative Learning Theory

• URL: http://arxiv.org/abs/2602.04402v2
• Date: Thu, 05 Feb 2026 20:34:59 GMT
• Title: Performative Learning Theory
• Authors: Julian Rodemann, Unai Fischer-Abaigar, James Bailie, Krikamol Muandet,
• Abstract summary: We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population.<n>We prove generalization bounds under performative effects on the sample, on the population, and on both.<n>Our analysis reveals a fundamental trade-off between performatively changing the world and learning from it.
• Score: 8.953630726489463
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only existing users of an app) and/or the whole population (e.g., all potential app users). This raises the question of how well models generalize under performativity. For example, how well can we draw insights about new app users based on existing users when both of them react to the app's predictions? We address this question by embedding performative predictions into statistical learning theory. We prove generalization bounds under performative effects on the sample, on the population, and on both. A key intuition behind our proofs is that in the worst case, the population negates predictions, while the sample deceptively fulfills them. We cast such self-negating and self-fulfilling predictions as min-max and min-min risk functionals in Wasserstein space, respectively. Our analysis reveals a fundamental trade-off between performatively changing the world and learning from it: the more a model affects data, the less it can learn from it. Moreover, our analysis results in a surprising insight on how to improve generalization guarantees by retraining on performatively distorted samples. We illustrate our bounds in a case study on prediction-informed assignments of unemployed German residents to job trainings, drawing upon administrative labor market records from 1975 to 2017 in Germany.

Related papers

• Scaling Open-Ended Reasoning to Predict the Future [56.672065928345525]
  We train language models to make predictions on open-ended forecasting questions.<n>To scale up training data, we synthesize novel forecasting questions from global events reported in daily news.<n>We find calibration improvements from forecasting training generalize across popular benchmarks.
  arXiv  Detail & Related papers  (2025-12-31T18:59:51Z)
• Trustworthy Prediction with Gaussian Process Knowledge Scores [7.090362431002478]
  Probabilistic models are often used to make predictions in regions of the data space where no observations are available.<n>We propose a knowledge score for predictions that quantifies the extent to which observing data have reduced our uncertainty about a prediction.<n>We demonstrate in several experiments that the knowledge score can anticipate when predictions from a GPR model are accurate.
  arXiv  Detail & Related papers  (2025-06-23T13:36:06Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Eliciting Uncertainty in Chain-of-Thought to Mitigate Bias against Forecasting Harmful User Behaviors [29.892041865029803]
  Conversation forecasting tasks a model with predicting the outcome of an unfolding conversation. It can be applied in social media moderation to predict harmful user behaviors before they occur. This paper explores what extent model uncertainty can be used as a tool to mitigate potential biases.
  arXiv  Detail & Related papers  (2024-10-17T15:07:53Z)
• Performative Prediction on Games and Mechanism Design [69.7933059664256]
  We study a collective risk dilemma where agents decide whether to trust predictions based on past accuracy.<n>As predictions shape collective outcomes, social welfare arises naturally as a metric of concern.<n>We show how to achieve better trade-offs and use them for mechanism design.
  arXiv  Detail & Related papers  (2024-08-09T16:03:44Z)
• ASPEST: Bridging the Gap Between Active Learning and Selective Prediction [56.001808843574395]
  Selective prediction aims to learn a reliable model that abstains from making predictions when uncertain. Active learning aims to lower the overall labeling effort, and hence human dependence, by querying the most informative examples. In this work, we introduce a new learning paradigm, active selective prediction, which aims to query more informative samples from the shifted target domain.
  arXiv  Detail & Related papers  (2023-04-07T23:51:07Z)
• Rationalizing Predictions by Adversarial Information Calibration [65.19407304154177]
  We train two models jointly: one is a typical neural model that solves the task at hand in an accurate but black-box manner, and the other is a selector-predictor model that additionally produces a rationale for its prediction. We use an adversarial technique to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features.
  arXiv  Detail & Related papers  (2023-01-15T03:13:09Z)
• Learning to Predict Trustworthiness with Steep Slope Loss [69.40817968905495]
  We study the problem of predicting trustworthiness on real-world large-scale datasets. We observe that the trustworthiness predictors trained with prior-art loss functions are prone to view both correct predictions and incorrect predictions to be trustworthy. We propose a novel steep slope loss to separate the features w.r.t. correct predictions from the ones w.r.t. incorrect predictions by two slide-like curves that oppose each other.
  arXiv  Detail & Related papers  (2021-09-30T19:19:09Z)
• Competing AI: How does competition feedback affect machine learning? [14.350250426090893]
  We show that competition causes predictors to specialize for specific sub-populations at the cost of worse performance over the general population. We show that having too few or too many competing predictors in a market can hurt the overall prediction quality.
  arXiv  Detail & Related papers  (2020-09-15T00:13:32Z)
• How to "Improve" Prediction Using Behavior Modification [0.0]
  Data science researchers design algorithms, models, and approaches to improve prediction. Predictive accuracy is improved with larger and richer data. platforms can stealthily achieve better prediction accuracy by pushing users' behaviors towards their predicted values. Our derivation elucidates implications of such behavior modification to data scientists, platforms, their customers, and the humans whose behavior is manipulated.
  arXiv  Detail & Related papers  (2020-08-26T12:39:35Z)
• Counterfactual Predictions under Runtime Confounding [74.90756694584839]
  We study the counterfactual prediction task in the setting where all relevant factors are captured in the historical data. We propose a doubly-robust procedure for learning counterfactual prediction models in this setting.
  arXiv  Detail & Related papers  (2020-06-30T15:49:05Z)
• Performative Prediction [31.876692592395777]
  We develop a framework for performative prediction bringing together concepts from statistics, game theory, and causality. A conceptual novelty is an equilibrium notion we call performative stability. Our main results are necessary and sufficient conditions for the convergence of retraining to a performatively stable point of nearly minimal loss.
  arXiv  Detail & Related papers  (2020-02-16T20:29:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.