Abstract. Analysis of queries posed to open-domain question-answering systems indicates that particular types of queries are dominant, e.g., queries about the identity of people, a...
Increasingly, multi-agent systems are being designed for a variety of complex, dynamic domains. E ective agent interactions in such domains raise some of most fundamental research...
This paper proposes the use of constructive ordinals as mistake bounds in the on-line learning model. This approach elegantly generalizes the applicability of the on-line mistake ...
Standard no-internal-regret (NIR) algorithms compute a fixed point of a matrix, and hence typically require O(n3 ) run time per round of learning, where n is the dimensionality of...
Stability has been explored to study the performance of learning algorithms in recent years and it has been shown that stability is sufficient for generalization and is sufficient ...