no code implementations • 2 Jun 2015 • Martin Azizyan, Akshay Krishnamurthy, Aarti Singh
This paper studies the problem of estimating the covariance of a collection of vectors using only highly compressed measurements of each vector.
no code implementations • 3 May 2015 • Martin Azizyan, Yen-Chi Chen, Aarti Singh, Larry Wasserman
We study the risk of mode-based clustering.
no code implementations • 9 Jun 2014 • Larry Wasserman, Martin Azizyan, Aarti Singh
We provide explicit bounds on the error rate of the resulting clustering.
no code implementations • 9 Jun 2014 • Martin Azizyan, Aarti Singh, Larry Wasserman
We consider the problem of clustering data points in high dimensions, i. e. when the number of data points may be much smaller than the number of dimensions.
no code implementations • 3 Apr 2014 • Akshay Krishnamurthy, Martin Azizyan, Aarti Singh
Our theoretical results show that even a constant number of measurements per column suffices to approximate the principal subspace to arbitrary precision, provided that the number of vectors is large.
no code implementations • NeurIPS 2013 • Martin Azizyan, Aarti Singh, Larry Wasserman
While several papers have investigated computationally and statistically efficient methods for learning Gaussian mixtures, precise minimax bounds for their statistical performance as well as fundamental limits in high-dimensional settings are not well-understood.
no code implementations • 7 Apr 2012 • Martin Azizyan, Aarti Singh, Larry Wasserman
Semisupervised methods are techniques for using labeled data $(X_1, Y_1),\ldots,(X_n, Y_n)$ together with unlabeled data $X_{n+1},\ldots, X_N$ to make predictions.