A geometric proof of calibration
From MaRDI portal
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.
Recommendations
Cited in
(7)- An easier way to calibrate.
- Rabin's calibration theorem revisited
- Exponential weight approachability, applications to calibration and regret minimization
- Approachability, regret and calibration: implications and equivalences
- A note on a conjectured sharpness principle for probabilistic forecasting with calibration
- Opportunistic approachability and generalized no-regret problems
- Statistical calibration: a simplification of Foster's proof
This page was built for publication: A geometric proof of calibration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3169115)
