Defensive forecasting
Vladimir Vovk, Akimichi Takemura, Glenn Shafer
Abstract
We consider how to make probability forecasts of binary labels. Our main mathematical result is that for any continuous gambling strategy used for detecting disagreement between the forecasts and the actual labels, there exists a forecasting strategy whose forecasts are ideal as far as this gambling strategy is concerned. A forecasting strategy obtained in this way from a gambling strategy demonstrating a strong law of large numbers is simplified and studied empirically.
Create a lesson
Related papers
Reinforcement Learning Enables Scaling Generalist Robot Policy Improvement
Michal Korniak, Marco Bagatella, Ralf Römer et al.
Adaptive Multi Mode: Budget-Aware Routing of Optimizers By Online Landscape Probes
Benjamin Jacob Bodner
Navigating Disagreement Among Criteria for Evaluating Explanation Faithfulness
Grant Shanklin, Jiří Němeček, Asia Biega
Context--Answer Metamodels: Forecasting LLM Activations Before the First Answer Token
Tommy He, Thomas Jiralerspong
Systolic Linear Attention: Co-Designing Tile-Grouped Gated Delta Attention for TPUs
Gagik Amirkhanyan, Nuojin Cheng
Message-passing graph persistence
Jorge Luiz Franco, Arthur Queiroz Moura, Moacir Ponti et al.