Description
This text discusses the problem of predicting individual sequences and offers a comprehensive treatment of the topic. It differs from standard statistical approaches by not making any probabilistic assumptions about the data-generating mechanism. The focus is on using expert advice to construct prediction algorithms that perform well for all possible sequences. This approach is applied to various problems such as game playing, data compression, stock market investment, and pattern analysis. The nonstochastic standpoint used in the analysis often reveals interesting connections between these seemingly unrelated problems.
This important text and reference for researchers and students in machine learning, game theory, statistics and information theory offers a comprehensive treatment of the problem of predicting individual sequences. Unlike standard statistical approaches to forecasting, prediction of individual sequences does not impose any probabilistic assumption on the data-generating mechanism. Yet, prediction algorithms can be constructed that work well for all possible sequences, in the sense that their performance is always nearly as good as the best forecasting strategy in a given reference class. The central theme is the model of prediction using expert advice, a general framework within which many related problems can be cast and discussed. Repeated game playing, adaptive data compression, sequential investment in the stock market, sequential pattern analysis, and several other problems are viewed as instances of the experts' framework and analyzed from a common nonstochastic standpoint that often reveals new and intriguing connections.
Related Products
