This group brings together researchers from many disciplines to work on online learning, a framework in machine learning where data is available in a sequential manner. Our emphasis is on theory and fundamental questions.
This field is related to problems in statistics, stochastic optimisation, and game theory. It has recently attracted a lot of attention with the successes of artificial intelligence in games. It is a natural framework to gain a meaningful theoretical understanding for countless learning tasks, in settings that can be stochastic (performing well with random inputs) and adversarial (in a competition or with the presence of malicious users).