Truncated Matrix Completion - An Empirical Study
Not on the map. Why?
Abstract (arXiv)
Low-rank Matrix Completion (LRMC) describes the problem where we wish to recover missing entries of partially observed low-rank matrix. Most existing matrix completion work deals with sampling procedures that are independent of the underlying data values. While this assumption allows the derivation of nice theoretical guarantees, it seldom holds in real-world applications. In this paper, we consider various settings where the sampling mask is dependent on the underlying data values, motivated by applications in sensing, sequential decision-making, and recommender systems. Through a series of experiments, we study and compare the performance of various LRMC algorithms that were originally successful for data-independent sampling patterns.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 33 references that are in the map. First posted on arXiv 14 Apr 2025.
Builds on
11 of 33 references.
References · 11
- 2016Recommendations as Treatments: Debiasing Learning and Evaluationcited by 248
- 2022Implicit Regularization Towards Rank Minimization in ReLU Networkscited by 53
- 2021Causal Matrix Completioncited by 45
- 2018Imputation and low-rank estimation with Missing Not At Random datacited by 21
- 2021Matrix completion with data-dependent missingness probabilitiescited by 15
- 2015A Characterization of Deterministic Sampling Patterns for Low-Rank Matrix Completioncited by 13
- 2020Rank 2r iterative least squares: efficient recovery of ill-conditioned low rank matrices from few entriescited by 10
- 2021GNMR: A provable one-line algorithm for low rank matrix recoverycited by 10
- 2018Matrix completion with deterministic pattern - a geometric perspectivecited by 7
- 2021TenIPS: Inverse Propensity Sampling for Tensor Completioncited by 7
- 2020Escaping Saddle Points in Ill-Conditioned Matrix Completion with a Scalable Second Order Methodcited by 2
Built on by
Not cited yet.