Many approaches to active learning involve periodically training one classifier and choosing data points with the lowest confidence. An alternative approach is to periodically cho...
We derive the limiting form of the eigenvalue spectrum for sample covariance matrices produced from non-isotropic data. For the analysis of standard PCA we study the case where th...
Recent advancements in model-based reinforcement learning have shown that the dynamics of many structured domains (e.g. DBNs) can be learned with tractable sample complexity, desp...
Thomas J. Walsh, Sergiu Goschin, Michael L. Littma...
We study a variant of the classical circuit-lower-bound problems: proving lower bounds for sampling distributions given random bits. We prove a lower bound of 1 - 1/n(1) on the st...