Adaptive Multinomial Matrix Completion

TL;DR

This paper introduces an adaptive nuclear norm penalized maximum likelihood estimator for quantized matrix completion, providing theoretical guarantees and an efficient algorithm, applicable to recommender systems and multi-class classification.

Contribution

It develops a novel adaptive estimator for quantized matrix completion that does not require prior knowledge of the matrix rank or nuclear norm, with proven minimax optimality.

Findings

The estimator is minimax optimal under the model.

The proposed algorithm efficiently computes the estimator.

Experimental results support the theoretical guarantees.

Abstract

The task of estimating a matrix given a sample of observed entries is known as the \emph{matrix completion problem}. Most works on matrix completion have focused on recovering an unknown real-valued low-rank matrix from a random sample of its entries. Here, we investigate the case of highly quantized observations when the measurements can take only a small number of values. These quantized outputs are generated according to a probability distribution parametrized by the unknown matrix of interest. This model corresponds, for example, to ratings in recommender systems or labels in multi-class classification. We consider a general, non-uniform, sampling scheme and give theoretical guarantees on the performance of a constrained, nuclear norm penalized maximum likelihood estimator. One important advantage of this estimator is that it does not require knowledge of the rank or an upper bound on the nuclear norm of the unknown matrix and, thus, it is adaptive. We provide lower bounds showing that our estimator is minimax optimal. An efficient algorithm based on lifted coordinate gradient descent is proposed to compute the estimator. A limited Monte-Carlo experiment, using both simulated and real data is provided to support our claims.