A Geometric Proof of Calibration

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 a 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 [Foster, D. 1999. A proof of calibration via Blackwell's approachability theorem. Games Econom. Behav.29 73--78] in the case of binary outcomes) and highlights the intrinsic connection between approachability and calibration.

[1]  A. Dawid Comment: The Impossibility of Inductive Inference , 1985 .

[2]  Alvaro Sandroni,et al.  Calibration with Many Checking Rules , 2003, Math. Oper. Res..

[3]  Gábor Lugosi,et al.  Prediction, learning, and games , 2006 .

[4]  Dean P. Foster,et al.  A Proof of Calibration Via Blackwell's Approachability Theorem , 1999 .

[5]  S. Hart,et al.  A simple adaptive procedure leading to correlated equilibrium , 2000 .

[6]  Xiaohong Chen,et al.  Laws of Large Numbers for Hilbert Space-Valued Mixingales with Applications , 1996, Econometric Theory.

[7]  D. Fudenberg,et al.  An Easier Way to Calibrate , 1999 .

[8]  V. Rich Personal communication , 1989, Nature.

[9]  D. Palomar Convex primal decomposition for multicarrier linear MIMO transceivers , 2005, IEEE Transactions on Signal Processing.

[10]  Vianney Perchet Approchabilité, calibration et regret dans les jeux à observations partielles , 2010 .

[11]  D. Bertsekas,et al.  TWO-METRIC PROJECTION METHODS FOR CONSTRAINED OPTIMIZATION* , 1984 .

[12]  R. Vohra,et al.  Calibrated Learning and Correlated Equilibrium , 1996 .

[13]  Sham M. Kakade,et al.  Deterministic calibration and Nash equilibrium , 2004, J. Comput. Syst. Sci..

[14]  D. Blackwell An analog of the minimax theorem for vector payoffs. , 1956 .

[15]  David Oakes,et al.  Self-Calibrating Priors Do Not Exist , 1985 .

[16]  Y. Freund,et al.  Adaptive game playing using multiplicative weights , 1999 .

[17]  John N. Tsitsiklis,et al.  Online Learning with Sample Path Constraints , 2009, J. Mach. Learn. Res..