论文信息 - Forecasting Distributions with Experts Advice

Forecasting Distributions with Experts Advice

This paper considers forecasts of the distribution of data whose distribution function is possibly time varying. The forecast is achieved via time varying combinations of experts’ forecasts. We derive theoretical worse case bounds for general algorithms based on multiplicative updates of the combination weights. The bounds are useful to study the properties of forecast combinations when data are nonstationary and there is no unique best model. An application with an empirical study is used to highlight the results in practice.

Alessio Sancetta | Alessio Sancetta

[1] B. Hansen. Autoregressive Conditional Density Estimation , 1994 .

[2] Yuhong Yang. COMBINING FORECASTING PROCEDURES: SOME THEORETICAL RESULTS , 2004, Econometric Theory.

[3] J. Stock,et al. Combination forecasts of output growth in a seven-country data set , 2004 .

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

[5] A. P. Dawid,et al. Present position and potential developments: some personal views , 1984 .

[6] László Györfi,et al. Strongly consistent nonparametric forecasting and regression for stationary ergodic sequences , 1999, ArXiv.

[7] A. Dawid. Calibration-Based Empirical Probability , 1985 .

[8] Christian Genest,et al. Combining Probability Distributions: A Critique and an Annotated Bibliography , 1986 .

[9] Michael P. Clements,et al. Pooling of Forecasts , 2004 .

[10] G. Lugosi,et al. On Prediction of Individual Sequences , 1998 .

[11] Manfred K. Warmuth,et al. Tracking a Small Set of Experts by Mixing Past Posteriors , 2003, J. Mach. Learn. Res..

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

[13] Gary Chamberlain,et al. Econometrics and decision theory , 2000 .

[14] Mark Herbster,et al. Tracking the Best Expert , 1995, Machine Learning.