Partial estimation of covariance matrices

A classical approach to accurately estimating the covariance matrix I pound of a p-variate normal distribution is to draw a sample of size n > p and form a sample covariance matrix. However, many modern applications operate with much smaller sample sizes, thus calling for estimation guarantees in the regime . We show that a sample of size n = O(m log(6) p) is sufficient to accurately estimate in operator norm an arbitrary symmetric part of I pound consisting of m a parts per thousand currency sign n nonzero entries per row. This follows from a general result on estimating Hadamard products M center dot I pound, where M is an arbitrary symmetric matrix.