mlsanityData to 14 Oct 2026

In Defense of Defensive Forecasting

arXiv 2506.11848 ↗First posted 13 Jun 2025cs.LG stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 18 of its 38 references that are in the map. First posted on arXiv 13 Jun 2025.

Builds on

18 of 38 references.

References · 18

  1. 2020Performative Predictioncited by 327
  2. 2020Outcome Indistinguishabilitycited by 75
  3. 2021Omnipredictorscited by 74
  4. 2022Practical Adversarial Multivalid Conformal Predictioncited by 65
  5. 2022Loss Minimization through the Lens of Outcome Indistinguishabilitycited by 62
  6. 2022A Unifying Theory of Distance from Calibrationcited by 53
  7. 2021Online Multivalid Learning: Means, Moments, and Prediction Intervalscited by 49
  8. 2023High-Dimensional Prediction for Sequential Decision Makingcited by 41
  9. 2023Oracle Efficient Online Multicalibration and Omnipredictioncited by 37
  10. 2025Near-Optimal Algorithms for Omnipredictioncited by 33
  11. 2015On Equivalence of Martingale Tail Bounds and Deterministic Regret Inequalitiescited by 27
  12. 2021Online Minimax Multiobjective Optimization: Multicalibeating and Other Applicationscited by 27
6 more
  1. 2022Forecast Hedging and Calibrationcited by 22
  2. 2013Approachability, Regret and Calibration; implications and equivalencescited by 19
  3. 2024On the Distance from Calibration in Sequential Predictioncited by 19
  4. 2024Breaking the T2/3 Barrier for Sequential Calibrationcited by 19
  5. 2024From Fairness to Infinity: Outcome-Indistinguishable (Omni)Prediction in Evolving Graphscited by 13
  6. 2025Revisiting the Predictability of Performative, Social Eventscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026An Efficient Black-Box Reduction from Online Learning to Multicalibration, and a New Route to Phi-Regret Minimizationcited by 3
  2. 2026Defensive Generationcited by 1
  3. 2026Defensive Boosting for Online Probabilistic Forecastingcited by 0
  4. 2026A Unifying Perspective on Probabilities as Model Predictionscited by 0
  5. 2026Stabilizing Performative Feedback Loops with Minimal Model Deploymentscited by 0