Prediction-Powered E-Values

Daniel Csillag, Claudio Jose Struchiner, Guilherme Tegoni Goedert
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:11493-11514, 2025.

Abstract

Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising methodology, but existing approaches are largely limited to Z-estimation problems such as inference of means and quantiles. In this paper, we apply ideas of prediction-powered inference to e-values. By doing so, we inherit all the usual benefits of e-values – such as anytime-validity, post-hoc validity and versatile sequential inference – as well as greatly expand the set of inferences achievable in a prediction-powered manner. In particular, we show that every inference procedure that can be framed in terms of e-values has a prediction-powered counterpart, given by our method. We showcase the effectiveness of our framework across a wide range of inference tasks, from simple hypothesis testing and confidence intervals to more involved procedures for change-point detection and causal discovery, which were out of reach of previous techniques. Our approach is modular and easily integrable into existing algorithms, making it a compelling choice for practical applications.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-csillag25a, title = {Prediction-Powered E-Values}, author = {Csillag, Daniel and Struchiner, Claudio Jose and Goedert, Guilherme Tegoni}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {11493--11514}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/csillag25a/csillag25a.pdf}, url = {https://proceedings.mlr.press/v267/csillag25a.html}, abstract = {Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising methodology, but existing approaches are largely limited to Z-estimation problems such as inference of means and quantiles. In this paper, we apply ideas of prediction-powered inference to e-values. By doing so, we inherit all the usual benefits of e-values – such as anytime-validity, post-hoc validity and versatile sequential inference – as well as greatly expand the set of inferences achievable in a prediction-powered manner. In particular, we show that every inference procedure that can be framed in terms of e-values has a prediction-powered counterpart, given by our method. We showcase the effectiveness of our framework across a wide range of inference tasks, from simple hypothesis testing and confidence intervals to more involved procedures for change-point detection and causal discovery, which were out of reach of previous techniques. Our approach is modular and easily integrable into existing algorithms, making it a compelling choice for practical applications.} }
Endnote
%0 Conference Paper %T Prediction-Powered E-Values %A Daniel Csillag %A Claudio Jose Struchiner %A Guilherme Tegoni Goedert %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-csillag25a %I PMLR %P 11493--11514 %U https://proceedings.mlr.press/v267/csillag25a.html %V 267 %X Quality statistical inference requires a sufficient amount of data, which can be missing or hard to obtain. To this end, prediction-powered inference has risen as a promising methodology, but existing approaches are largely limited to Z-estimation problems such as inference of means and quantiles. In this paper, we apply ideas of prediction-powered inference to e-values. By doing so, we inherit all the usual benefits of e-values – such as anytime-validity, post-hoc validity and versatile sequential inference – as well as greatly expand the set of inferences achievable in a prediction-powered manner. In particular, we show that every inference procedure that can be framed in terms of e-values has a prediction-powered counterpart, given by our method. We showcase the effectiveness of our framework across a wide range of inference tasks, from simple hypothesis testing and confidence intervals to more involved procedures for change-point detection and causal discovery, which were out of reach of previous techniques. Our approach is modular and easily integrable into existing algorithms, making it a compelling choice for practical applications.
APA
Csillag, D., Struchiner, C.J. & Goedert, G.T.. (2025). Prediction-Powered E-Values. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:11493-11514 Available from https://proceedings.mlr.press/v267/csillag25a.html.

Related Material