Why are big data matrices approximately low rank?

M Udell, A Townsend - SIAM Journal on Mathematics of Data Science, 2019‏ - SIAM
Matrices of (approximate) low rank are pervasive in data science, appearing in movie
preferences, text documents, survey data, medical records, and genomics. While there is a …

Patch2Self: Denoising Diffusion MRI with Self-Supervised Learning​

S Fadnavis, J Batson… - Advances in Neural …, 2020‏ - proceedings.neurips.cc
Diffusion-weighted magnetic resonance imaging (DWI) is the only non-invasive method for
quantifying microstructure and reconstructing white-matter pathways in the living human …

Explaining the success of nearest neighbor methods in prediction

GH Chen, D Shah - Foundations and Trends® in Machine …, 2018‏ - nowpublishers.com
Many modern methods for prediction leverage nearest neighbor search to find past training
examples most similar to a test example, an idea that dates back in text to at least the 11th …

Causal matrix completion

A Agarwal, M Dahleh, D Shah… - The thirty sixth annual …, 2023‏ - proceedings.mlr.press
Matrix completion is the study of recovering an underlying matrix from a sparse subset of
noisy observations. Traditionally, it is assumed that the entries of the matrix are “missing …

On robustness of principal component regression

A Agarwal, D Shah, D Shen… - Advances in Neural …, 2019‏ - proceedings.neurips.cc
Consider the setting of Linear Regression where the observed response variables, in
expectation, are linear functions of the p-dimensional covariates. Then to achieve vanishing …

Rates of convergence of spectral methods for graphon estimation

J Xu - International Conference on Machine Learning, 2018‏ - proceedings.mlr.press
This paper studies the problem of estimating the graphon function–a generative mechanism
for a class of random graphs that are useful approximations to real networks. Specifically, a …

Missing not at random in matrix completion: The effectiveness of estimating missingness probabilities under a low nuclear norm assumption

W Ma, GH Chen - Advances in neural information …, 2019‏ - proceedings.neurips.cc
Matrix completion is often applied to data with entries missing not at random (MNAR). For
example, consider a recommendation system where users tend to only reveal ratings for …

Algebraic variety models for high-rank matrix completion

G Ongie, R Willett, RD Nowak… - … on Machine Learning, 2017‏ - proceedings.mlr.press
We consider a non-linear generalization of low-rank matrix completion to the case where the
data belongs to an algebraic variety, ie, each data point is a solution to a system of …

Counterfactual inference for sequential experiments

R Dwivedi, K Tian, S Tomkins, P Klasnja… - arxiv preprint arxiv …, 2022‏ - arxiv.org
We consider after-study statistical inference for sequentially designed experiments wherein
multiple units are assigned treatments for multiple time points using treatment policies that …

Model agnostic time series analysis via matrix estimation

A Agarwal, MJ Amjad, D Shah, D Shen - Proceedings of the ACM on …, 2018‏ - dl.acm.org
We propose an algorithm to impute and forecast a time series by transforming the observed
time series into a matrix, utilizing matrix estimation to recover missing values and de-noise …