|제 목 :||Universal Information Processing|
|연 사 :||Prof. Young-han Kim, University of California, San Diego|
|내 용 :|
| How can we compress data with the minimum number of bits? How can we invest money in the stock market with the maximum growth of wealth? Or how can we predict the future from the past with the least amount of distortion? Over the past four decades, several algorithms have been developed for such tasks that achieve essentially optimal performance with no prior knowledge about the statistical properties of the data.
This talk provides a broad introduction to theoretical foundations of such universal information processing algorithms for stochastic (random data) and individual sequence (nonrandom data) settings. We focus on three main topics-universal data compression (probability estimation)_., universal portfolio, and universal prediction – and discuss mathematical properties of universal algorithms and their implementation issues. We briefly explore additional topics such as universal filtering and universal estimation of entropy and mutual information.