Guardado en:
Detalles Bibliográficos
Autores principales: Perdomo, Juan Carlos, Recht, Benjamin
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2506.11848
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912669531897856
author Perdomo, Juan Carlos
Recht, Benjamin
author_facet Perdomo, Juan Carlos
Recht, Benjamin
contents This tutorial provides a survey of algorithms for Defensive Forecasting, where predictions are derived not by prognostication but by correcting past mistakes. Pioneered by Vovk, Defensive Forecasting frames the goal of prediction as a sequential game, and derives predictions to minimize metrics no matter what outcomes occur. We present an elementary introduction to this general theory and derive simple, near-optimal algorithms for online learning, calibration, prediction with expert advice, and online conformal prediction.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11848
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle In Defense of Defensive Forecasting
Perdomo, Juan Carlos
Recht, Benjamin
Machine Learning
This tutorial provides a survey of algorithms for Defensive Forecasting, where predictions are derived not by prognostication but by correcting past mistakes. Pioneered by Vovk, Defensive Forecasting frames the goal of prediction as a sequential game, and derives predictions to minimize metrics no matter what outcomes occur. We present an elementary introduction to this general theory and derive simple, near-optimal algorithms for online learning, calibration, prediction with expert advice, and online conformal prediction.
title In Defense of Defensive Forecasting
topic Machine Learning
url https://arxiv.org/abs/2506.11848