Predictions as Statements and Decisions

Prediction is a complex notion, and different predictors (such as people, computer programs, and probabilistic theories) can pursue very different goals. In this talk I will review some popular kinds of prediction and argue that the theory of competitive on-line learning can benefit from the kinds of prediction that are now foreign to it.

[1]  G. Gruenhage.  The Story of a Topological Game , 2006 .

[2]  Y. Cho,et al.  Fixed Point Theory and Applications , 2000 .

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

[4]  Akimichi Takemura,et al.  Defensive Forecasting for Linear Protocols , 2005, ALT.

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

[6]  T. Kuhn,et al.  The Structure of Scientific Revolutions. , 1964 .

[8]  Herbert Meschkowski,et al.  Hilbertsche Räume mit Kernfunktion , 1962 .

[9]  R. Mises,et al.  Wahrscheinlichkeit, Statistik und Wahrheit. , 1936 .

[10]  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 .

[11]  A. N. Kolmogorov,et al.  Foundations of the theory of probability , 1960 .

[12]  Andrei N. Kolmogorov,et al.  Logical basis for information theory and probability theory , 1968, IEEE Trans. Inf. Theory.

[13]  M. Kendall.  Theoretical Statistics , 1956, Nature.

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

[15]  Akimichi Takemura,et al.  Defensive Forecasting , 2005, AISTATS.

[16]  Péter Gács,et al.  Uniform test of algorithmic randomness over a general space , 2003, Theor. Comput. Sci..

[17]  Vladimir Vovk.  Competitive on-line learning with a convex loss function , 2005, ArXiv.

[18]  A. N. Kolmogorov.  Combinatorial foundations of information theory and the calculus of probabilities , 1983 .

[19]  Don R. Hush,et al.  Function Classes That Approximate the Bayes Risk , 2006, COLT.

[20]  Vladimir Vovk.  Defensive Prediction with Expert Advice , 2005, ALT.

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

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

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

[24]  V. Vovk,et al.  On the Empirical Validity of the Bayesian Method , 1993 .

[25]  Vladimir Vovk,et al.  On-Line Regression Competitive with Reproducing Kernel Hilbert Spaces , 2005, TAMC.

[26]  A. Berlinet,et al.  Reproducing kernel Hilbert spaces in probability and statistics , 2004 .

[27]  S. S. Wilks,et al.  Probability, statistics and truth , 1939 .

[28]  K. Popper,et al.  Logik der Forschung , 1935 .

[29]  N. Aronszajn.  Theory of Reproducing Kernels. , 1950 .

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

[31]  Yuri Kalnishkan,et al.  The weak aggregating algorithm and weak mixability , 2005, J. Comput. Syst. Sci..

[32]  Vladimir Vovk,et al.  Aggregating strategies , 1990, COLT '90.

[33]  J. Moser.  A rapidly convergent iteration method and non-linear partial differential equations - I , 1966 .

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

[35]  Vladimir Vovk,et al.  Universal portfolio selection , 1998, COLT' 98.

[36]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2006 .

[37]  H. Brezis,et al.  Composition in fractional Sobolev spaces , 2001 .

[38]  Ingo Steinwart,et al.  On the Influence of the Kernel on the Consistency of Support Vector Machines , 2002, J. Mach. Learn. Res..

[39]  A. Kolmogorov.  Three approaches to the quantitative definition of information , 1968 .

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

[41]  G. Shafer.  The Unity and Diversity of Probability , 1990 .

[42]  Vladimir Vovk.  Non-asymptotic calibration and resolution , 2007, Theor. Comput. Sci..

[43]  Per Martin-Löf,et al.  The Definition of Random Sequences , 1966, Inf. Control..