28
13

Breaking the 1/n1/\sqrt{n} Barrier: Faster Rates for Permutation-based Models in Polynomial Time

Abstract

Many applications, including rank aggregation and crowd-labeling, can be modeled in terms of a bivariate isotonic matrix with unknown permutations acting on its rows and columns. We consider the problem of estimating such a matrix based on noisy observations of a subset of its entries, and design and analyze a polynomial-time algorithm that improves upon the state of the art. In particular, our results imply that any such n×nn \times n matrix can be estimated efficiently in the normalized Frobenius norm at rate O~(n3/4)\widetilde{\mathcal O}(n^{-3/4}), thus narrowing the gap between O~(n1)\widetilde{\mathcal O}(n^{-1}) and O~(n1/2)\widetilde{\mathcal O}(n^{-1/2}), which were hitherto the rates of the most statistically and computationally efficient methods, respectively.

View on arXiv
Comments on this paper