Computational Learning Theory (COLT) is a research field devoted to studying the design and analysis of adaptive algorithms. This includes algorithms that make predictions about the future based on past observations, algorithms that learn from a teacher, and algorithms that learn by interacting with the world around them.
The emphasis in COLT is on rigorous mathematical analysis. As a field with roots in theoretical computer science, COLT is largely concerned with computational and data efficiency. Much of the work in COLT can be traced to Valiant’s seminal paper on “A theory of the learnable” (1984) as well as Gold’s “Language identification in the limit” (1967).
The annual Conference on Computational Learning Theory began in 1988; the European Conference on Computational Learning Theory and the Workshop on Algorithmic Learning Theory were formed soon after. COLT has strongly encouraged interaction with other fields that work on problems of prediction such as applied machine learning, statistics, information theory, pattern recognition and statistical physics, as well as other areas of computer science such as artificial intelligence, complexity theory and cryptography.