Conformalized Tensor Completion with Riemannian Optimization

TL;DR

This paper introduces a novel method for quantifying uncertainty in tensor completion tasks using conformal prediction, leveraging Riemannian optimization and tensor Ising models to improve estimation accuracy and reliability.

Contribution

It develops a conformal prediction framework for tensor completion, connecting uncertainty quantification to missing data propensity estimation with a Riemannian gradient descent approach.

Findings

Valid conformal intervals demonstrated through simulations

Effective tensor parameter estimation via Riemannian gradient descent

Successful application to TEC reconstruction problem

Abstract

Tensor data, or multi-dimensional arrays, is a data format popular in multiple fields such as social network analysis, recommender systems, and brain imaging. It is not uncommon to observe tensor data containing missing values, and tensor completion aims at estimating the missing values given the partially observed tensor. Sufficient efforts have been spared on devising scalable tensor completion algorithms, but few on quantifying the uncertainty of the estimator. In this paper, we nest the uncertainty quantification (UQ) of tensor completion under a split conformal prediction framework and establish the connection of the UQ problem to a problem of estimating the missing propensity of each tensor entry. We model the data missingness of the tensor with a tensor Ising model parameterized by a low-rank tensor parameter. We propose to estimate the tensor parameter by maximum pseudo-likelihood estimation (MPLE) with a Riemannian gradient descent algorithm. Extensive simulation studies have been conducted to justify the validity of the resulting conformal interval. We apply our method to the regional total electron content (TEC) reconstruction problem. Supplemental materials of the paper are available online.