LGMLJun 13, 2025

In Defense of Defensive Forecasting

arXiv:2506.11848v23 citationsh-index: 10
Originality Synthesis-oriented
AI Analysis

It provides a tutorial on an incremental approach to prediction theory for researchers in online learning and forecasting.

The paper introduces Defensive Forecasting as a sequential game framework for deriving predictions by correcting past errors, and presents simple, near-optimal algorithms for tasks like online learning and calibration.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes