Why are Big Data Matrices Approximately Low Rank?

v1v2 (latest)

Why are Big Data Matrices Approximately Low Rank?

21 May 2017

Madeleine Udell

ArXiv (abs)PDF HTML

Papers citing "Why are Big Data Matrices Approximately Low Rank?"

13 / 13 papers shown

Title
Nonparametric Matrix Estimation with One-Sided Covariates Chao Yu 192 5 0 26 Oct 2021
On Model Identification and Out-of-Sample Prediction of Principal Component Regression: Applications to Synthetic Controls Anish Agarwal Devavrat Shah Dennis Shen 399 2 0 27 Oct 2020
On Robustness of Principal Component RegressionNeural Information Processing Systems (NeurIPS), 2019 Anish Agarwal Devavrat Shah Dennis Shen Dogyoon Song 549 83 0 28 Feb 2019
Imputation and low-rank estimation with Missing Not At Random data Aude Sportisse Claire Boyer Julie Josse 203 54 0 29 Dec 2018
Consistent polynomial-time unseeded graph matching for Lipschitz graphons Yuan Zhang 96 4 0 29 Jul 2018
Unseeded low-rank graph matching by transform-based unsupervised point registration Yuan Zhang 124 7 0 12 Jul 2018
Causal Inference with Noisy and Missing Covariates via Matrix Factorization Nathan Kallus Xiaojie Mao Madeleine Udell CML 137 66 0 03 Jun 2018
Intrinsic Complexity And Scaling Laws: From Random Fields to Random Vectors Jennifer Bryson Hongkai Zhao Yimin Zhong 115 3 0 01 May 2018
Spectral State Compression of Markov Processes Anru R. Zhang Mengdi Wang 165 55 0 08 Feb 2018
Robust Synthetic Control M. Amjad Devavrat Shah Dennis Shen 201 151 0 18 Nov 2017
Randomized Nonnegative Matrix Factorization N. Benjamin Erichson Ariana Mendible Sophie Wihlborn J. Nathan Kutz 160 54 0 06 Nov 2017
Matchability of heterogeneous networks pairs V. Lyzinski D. Sussman 250 5 0 05 May 2017
Dynamic Assortment Personalization in High Dimensions Nathan Kallus Madeleine Udell 354 74 0 18 Oct 2016