We show that the disagreement coefficient of certain smooth hypothesis classes is O(m), where m is the dimension of the hypothesis space, thereby answering a question posed in [Fri09]. We answer aâ€¦ (More)

We consider the problem of choosing a density estimate from a set of densities F , minimizing the L1-distance to an unknown distribution. Devroye and Lugosi [DL01] analyze two algorithms for theâ€¦ (More)

We consider the problem of computing L1-distances between every pair of probability densities from a given family. We point out that the technique of Cauchy random projections [Ind06] in this contextâ€¦ (More)

We consider the problem of estimating the parameters of a mixture of distributions, where each component distribution is from a given parametric family e.g. exponential, Gaussian etc. We define aâ€¦ (More)

Given a Gaussian Markov random field, we consider the problem of selecting a subset of variables to observe which minimizes the total expected squared prediction error of the unobserved variables. Weâ€¦ (More)