Thomas Kehrenberg
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Thomas Kehrenberg has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Francisco Javier Sanguino Bautiste
Basque Center for Applied Mathematics, Bilbao, Spain
2 shared publications - Jose Antonio Lozano
Basque Center for Applied Mathematics (BCAM)
2 shared publications - Novi Quadrianto
University of Sussex, Brighton, United Kingdom, and Basque Center for Applied Mathematics, Bilbao, Spain
2 shared publications
Latest Publications
- Open Access
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 3190-3216
Strategically Deceptive Model Deployment in Performative Prediction
- 25 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 3190-3216
Open AccessStrategically Deceptive Model Deployment in Performative Prediction
- Open Access
- 24 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (13) , 1-35
Dissecting Performative Prediction: A Comprehensive Survey
The field of performative prediction had its beginnings in 2020 with the seminal article “Performative Prediction” by Perdomo et al., which established a novel machine learning setup where the deployment of a predictive model causes a distribution shift in the environment, which in turn causes a mismatch between the distribution expected by the predictive model and the real distribution. This shift is defined by a so-called distribution map. In the half-decade since, a literature has emerged which has, among other things, introduced new solution concepts to the original setup, extended the setup, offered new theoretical analyses, and examined the intersection of performative prediction and other established fields. In this survey, we first lay out the performative prediction setting and explain the different optimization targets: performative stability and performative optimality. We introduce a new way of classifying different performative prediction settings, based on how much information is available about the distribution map. We survey existing implementations of distribution maps and existing methods to address the problem of performative prediction, while examining different ways to categorize them. Finally, we point out known and previously unknown connections that can be drawn to other fields, in the hopes of stimulating future research.
- 24 June 2026
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (13) , 1-35
Open AccessDissecting Performative Prediction: A Comprehensive Survey
The field of performative prediction had its beginnings in 2020 with the seminal article “Performative Prediction” by Perdomo et al., which established a novel machine learning setup where the deployment of a predictive model causes a distribution shift in the environment, which in turn causes a mismatch between the distribution expected by the predictive model and the real distribution. This shift is defined by a so-called distribution map. In the half-decade since, a literature has emerged which has, among other things, introduced new solution concepts to the original setup, extended the setup, offered new theoretical analyses, and examined the intersection of performative prediction and other established fields. In this survey, we first lay out the performative prediction setting and explain the different optimization targets: performative stability and performative optimality. We introduce a new way of classifying different performative prediction settings, based on how much information is available about the distribution map. We survey existing implementations of distribution maps and existing methods to address the problem of performative prediction, while examining different ways to categorize them. Finally, we point out known and previously unknown connections that can be drawn to other fields, in the hopes of stimulating future research.