PAC-Bayesian lifelong learning for multi-armed bandits

Abstract

We present a PAC-Bayesian analysis of lifelong learning. In the lifelong learning problem, a sequence of learning tasks is observed one-at-a-time, and the goal is to transfer information acquired from previous tasks to new learning tasks. We consider the case when each learning task is a multi-armed bandit problem. We derive lower bounds on the expected average reward that would be obtained if a given multi-armed bandit algorithm was run in a new task with a particular prior and for a set number of steps. We propose lifelong learning algorithms that use our new bounds as learning objectives. Our proposed algorithms are evaluated in several lifelong multi-armed bandit problems and are found to perform better than a baseline method that does not use generalisation bounds.

Deep Learning Theories and Methods for Breast Cancer Classification

“…Lifelong learning, a concept inspired by the way humans continually acquire and adapt knowledge throughout their lives, can significantly contribute to the improvement of breast cancer detection and diagnosis in several ways [70]. Lifelong learning systems can continuously update their knowledge and adapt to new information and techniques in the field of breast cancer detection [71].…”