Concentration properties of fractional posterior in 1-bit matrix completion
This work offers theoretical guarantees for Bayesian methods in binary matrix completion, which is incremental but important for applications like recommendation systems with binary data.
The paper addresses the lack of theoretical exploration of Bayesian methods in 1-bit matrix completion by providing concentration results for the fractional posterior under a non-uniform sampling scheme, demonstrating effective recovery of the underlying parameter matrix with adaptive rank estimation and fewer assumptions than frequentist approaches.
The problem of estimating a matrix based on a set of its observed entries is commonly referred to as the matrix completion problem. In this work, we specifically address the scenario of binary observations, often termed as 1-bit matrix completion. While numerous studies have explored Bayesian and frequentist methods for real-value matrix completion, there has been a lack of theoretical exploration regarding Bayesian approaches in 1-bit matrix completion. We tackle this gap by considering a general, non-uniform sampling scheme and providing theoretical assurances on the efficacy of the fractional posterior. Our contributions include obtaining concentration results for the fractional posterior and demonstrating its effectiveness in recovering the underlying parameter matrix. We accomplish this using two distinct types of prior distributions: low-rank factorization priors and a spectral scaled Student prior, with the latter requiring fewer assumptions. Importantly, our results exhibit an adaptive nature by not mandating prior knowledge of the rank of the parameter matrix. Our findings are comparable to those found in the frequentist literature, yet demand fewer restrictive assumptions.