中央研究院 資訊科學研究所

A common practice in machine learning is to learn a model (e.g. a classifier) in a batch way, in which one first collects a set of training examples and then learns a model from this training set. Afterwards, the learned model is used for all the future testing data, but it remains fixed without being further updated. While this is sufficient for many applications considered today, it may not work well for others. In fact, this does not seem to be the way we humans usually learn. This motivates the study of learning in the online setting, in which the learning process never stops as long as new data keeps coming. In this talk, we will discuss the work we have done in this direction, focusing on the theoretical foundation and its application to game theory. 

 

   Chi-Jen Lu received his B.S. and M.S. degrees in information engineering and computer science from National Taiwan University in 1988 and 1990 respectively. After two years of military service, he went to University of Massachusetts at Amherst, and received a Ph.D. degree in computer science in Feb. of 1999. Then he was an assistant professor of the computer science and information engineering department of National Chi-Nan University. He joined the Institute of Information Science as an assistant research fellow in Aug. of 1999.

    His research interests include machine learning, game theory, computational complexity, and algorithms.