(weak) Calibration is Computationally Hard

We show that the existence of a computationally efficient calibration algorithm, with a low weak calibration rate, would imply the existence of an efficient algorithm for computing approximate Nash equilibria - thus implying the unlikely conclusion that every problem in PPAD is solvable in polynomial time.

[1]  A. Dawid.  The Well-Calibrated Bayesian , 1982 .

[2]  G. Blattenberger,et al.  Separating the Brier Score into Calibration and Refinement Components: A Graphical Exposition , 1985 .

[3]  Christos H. Papadimitriou,et al.  On the Complexity of the Parity Argument and Other Inefficient Proofs of Existence , 1994, J. Comput. Syst. Sci..

[4]  Dean P. Foster,et al.  Calibrated Learning and Correlated Equilibrium , 1997 .

[5]  E. Kalai,et al.  Calibrated Forecasting and Merging , 1999 .

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

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

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

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

[10]  Shie Mannor,et al.  Online calibrated forecasts: Memory efficiency versus universality for learning in games , 2006, Machine Learning.

[11]  Xiaotie Deng,et al.  Settling the complexity of computing two-player Nash equilibria , 2007, JACM.

[12]  Constantinos Daskalakis,et al.  Nash equilibria: Complexity, symmetries, and approximation , 2009, Comput. Sci. Rev..

[13]  Vianney Perchet,et al.  Calibration and Internal No-Regret with Random Signals , 2009, ALT.

[14]  Shie Mannor,et al.  A Geometric Proof of Calibration , 2009, Math. Oper. Res..

[15]  Ambuj Tewari,et al.  Online Learning: Beyond Regret , 2010, COLT.

[16]  Shie Mannor,et al.  Does an Efficient Calibrated Forecasting Strategy Exist? , 2011, COLT.

[17]  Peter L. Bartlett,et al.  Blackwell Approachability and No-Regret Learning are Equivalent , 2010, COLT.