We develop a theory for learning scenarios where multiple learners co-exist but there are mutual compatibility constraints on their outcomes. This is natural in cognitive learning...
Unsupervised sequence learning is important to many applications. A learner is presented with unlabeled sequential data, and must discover sequential patterns that characterize th...
This paper analyzes the potential advantages and theoretical challenges of “active learning” algorithms. Active learning involves sequential sampling procedures that use infor...
We state and analyze the first active learning algorithm which works in the presence of arbitrary forms of noise. The algorithm, A2 (for Agnostic Active), relies only upon the ass...
Maria-Florina Balcan, Alina Beygelzimer, John Lang...
We present a model for sentence compression that uses a discriminative largemargin learning framework coupled with a novel feature set defined on compressed bigrams as well as dee...