A Geometric Proof of Calibration
Shie Mannor (EE-Technion), Gilles Stoltz (DMA, GREGH)

TL;DR
This paper presents a concise geometric proof of the existence of calibrated forecasters for any finite outcome set, emphasizing the link between approachability theory and calibration.
Contribution
It offers a new, simple proof applicable to multiple outcomes, illustrating the connection between Blackwell's approachability and calibration.
Findings
Proof valid for any finite number of outcomes
Highlights the link between approachability and calibration
Simplifies existing proofs using geometric approach
Abstract
We provide yet another proof of the existence of calibrated forecasters; it has two merits. First, it is valid for an arbitrary finite number of outcomes. Second, it is short and simple and it follows from a direct application of Blackwell's approachability theorem to carefully chosen vector-valued payoff function and convex target set. Our proof captures the essence of existing proofs based on approachability (e.g., the proof by Foster, 1999 in case of binary outcomes) and highlights the intrinsic connection between approachability and calibration.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsForecasting Techniques and Applications · Scientific Measurement and Uncertainty Evaluation
