Defensive Forecasting

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.

[1]  G. Shafer,et al.  Good randomized sequential probability forecasting is always possible , 2005 .

[2]  E. Lehrer Any Inspection is Manipulable , 2001 .

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

[4]  Dirk van Dalen,et al.  Arguments for the continuity principle , 1999, Bull. Symb. Log..

[5]  A. H. Murphy,et al.  Verification of Probabilistic Predictions: A Brief Review , 1967 .

[6]  G. Shafer,et al.  Probability and Finance: It's Only a Game! , 2001 .

[7]  William H. Press,et al.  Numerical recipes in C , 2002 .

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

[9]  P. Martin-Löf Notes on constructive mathematics , 1970 .

[10]  K. Parthasarathy,et al.  Positive Definite Kernels, Continuous Tensor Products, and Central Limit Theorems of Probability Theory , 1972 .

[11]  Jean-Luc Ville Étude critique de la notion de collectif , 1939 .

[12]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[13]  V. Vovk Competitive On‐line Statistics , 2001 .

[14]  A. Dawid Self-Calibrating Priors Do Not Exist: Comment , 1985 .

[15]  M. Duflo,et al.  Sur la loi des grands nombres pour les martingales vectorielles et l'estimateur des moindres carrés d'un modèle de régression , 1990 .

[16]  S. Smale,et al.  On a theory of computation and complexity over the real numbers; np-completeness , 1989 .

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

[18]  J. Doob Stochastic processes , 1953 .

[19]  L. E. J. Brouwer,et al.  Begründung der Mengenlehre unabhängig vom logischen Satz vom ausgeschlossenen Dritten , 2022 .

[20]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .