TenIPS: Inverse Propensity Sampling for Tensor Completion

Abstract

Tensors are widely used to represent multiway arrays of data. The recovery of missing entries in a tensor has been extensively studied, generally under the assumption that entries are missing completely at random (MCAR). However, in most practical settings, observations are missing not at random (MNAR): the probability that a given entry is observed (also called the propensity) may depend on other entries in the tensor or even on the value of the missing entry. In this paper, we study the problem of completing a partially observed tensor with MNAR observations, without prior information about the propensities. To complete the tensor, we assume that both the original tensor and the tensor of propensities have low multilinear rank. The algorithm first estimates the propensities using a convex relaxation and then predicts missing values using a higher-order SVD approach, reweighting the observed tensor by the inverse propensities. We provide finite-sample error bounds on the resulting complete tensor. Numerical experiments demonstrate the effectiveness of our approach.

arXiv commentAISTATS 2021

References in corpus (11)

• Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
• Square Deal: Lower Bounds and Improved Relaxations for Tensor Recovery
• Estimation of low-rank tensors via convex optimization
• Generalized Canonical Polyadic Tensor Decomposition
• Provable Tensor Factorization with Missing Data
• A Max-Norm Constrained Minimization Approach to 1-Bit Matrix Completion
• Learning tensors from partial binary measurements
• Tensor Completion by Alternating Minimization under the Tensor Train (TT) Model
• Missing Not at Random in Matrix Completion: The Effectiveness of Estimating Missingness Probabilities Under a Low Nuclear Norm Assumption
• Low-Rank Tucker Approximation of a Tensor From Streaming Data
• HOSVD-Based Algorithm for Weighted Tensor Completion