Competing with Stationary Prediction Strategies

This paper introduces the class of stationary prediction strategies and constructs a prediction algorithm that asymptotically performs as well as the best continuous stationary strategy. We make mild compactness assumptions but no stochastic assumptions about the environment. In particular, no assumption of stationarity is made about the environment, and the stationarity of the considered strategies only means that they do not depend explicitly on time; it is natural to consider only stationary strategies for many non-stationary environments.

[1]  Vladimir Vovk,et al.  Predictions as Statements and Decisions , 2006, COLT.

[2]  P. Algoet.  UNIVERSAL SCHEMES FOR PREDICTION, GAMBLING AND PORTFOLIO SELECTION' , 1992 .

[3]  Lenore Blum,et al.  Complexity and Real Computation , 1997, Springer New York.

[4]  Manfred K. Warmuth,et al.  The Weighted Majority Algorithm , 1994, Inf. Comput..

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

[6]  Philip M. Long,et al.  WORST-CASE QUADRATIC LOSS BOUNDS FOR ON-LINE PREDICTION OF LINEAR FUNCTIONS BY GRADIENT DESCENT , 1993 .

[7]  H. Joseph Newton,et al.  A Conversation with Emanuel Parzen , 2002 .

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

[9]  Andrew B. Nobel,et al.  On optimal sequential prediction for general processes , 2003, IEEE Trans. Inf. Theory.

[10]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series , 1964 .

[11]  Philip M. Long,et al.  Worst-case quadratic loss bounds for prediction using linear functions and gradient descent , 1996, IEEE Trans. Neural Networks.

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

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

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

[15]  Claudio Gentile,et al.  Adaptive and Self-Confident On-Line Learning Algorithms , 2000, J. Comput. Syst. Sci..

[16]  D. Ornstein.  Guessing the next output of a stationary process , 1978 .

[17]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[18]  Alfredo De Santis,et al.  Learning probabilistic prediction functions , 1988, [Proceedings 1988] 29th Annual Symposium on Foundations of Computer Science.

[19]  G. Lugosi,et al.  Strategies for Sequential Prediction of Stationary Time Series , 2000 .

[20]  S. Vajda,et al.  Contribution to the Theory of Games , 1951 .

[21]  Manfred K. Warmuth,et al.  Averaging Expert Predictions , 1999, EuroCOLT.

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

[23]  Stephen E. Fienberg,et al.  Testing Statistical Hypotheses , 2005 .

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

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

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

[27]  J. Doob.  Stochastic processes , 1953 .

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

[29]  Norbert Wiener,et al.  Extrapolation, Interpolation, and Smoothing of Stationary Time Series, with Engineering Applications , 1949 .

[30]  László Györfi,et al.  A Simple Randomized Algorithm for Consistent Sequential Prediction of Ergodic time Series , 1998 .

[31]  A. N. Kolmogorov,et al.  Interpolation and extrapolation of stationary random sequences. , 1962 .