Guaranteed rank minimization via singular value projection
Minimizing the rank of a matrix subject to affine constraints is a fundamental problem with
many important applications in machine learning and statistics. In this paper we propose a …
many important applications in machine learning and statistics. In this paper we propose a …
Missing data recovery by exploiting low-dimensionality in power system synchrophasor measurements
This paper presents a new framework of recovering missing synchrophasor measurements
(erasures). Leveraging the approximate low-rank property of phasor measurement unit …
(erasures). Leveraging the approximate low-rank property of phasor measurement unit …
Fast differentially private matrix factorization
Differentially private collaborative filtering is a challenging task, both in terms of accuracy
and speed. We present a simple algorithm that is provably differentially private, while …
and speed. We present a simple algorithm that is provably differentially private, while …
Mixed dimension embeddings with application to memory-efficient recommendation systems
Embedding representations power machine intelligence in many applications, including
recommendation systems, but they are space intensive-potentially occupying hundreds of …
recommendation systems, but they are space intensive-potentially occupying hundreds of …
Collaborative filtering in a non-uniform world: Learning with the weighted trace norm
N Srebro, RR Salakhutdinov - Advances in neural …, 2010 - proceedings.neurips.cc
We show that matrix completion with trace-norm regularization can be significantly hurt
when entries of the matrix are sampled non-uniformly, but that a properly weighted version …
when entries of the matrix are sampled non-uniformly, but that a properly weighted version …
The missing piece in complex analytics: Low latency, scalable model management and serving with velox
To support complex data-intensive applications such as personalized recommendations,
targeted advertising, and intelligent services, the data management community has focused …
targeted advertising, and intelligent services, the data management community has focused …
Fixed-rank matrix factorizations and Riemannian low-rank optimization
Motivated by the problem of learning a linear regression model whose parameter is a large
fixed-rank non-symmetric matrix, we consider the optimization of a smooth cost function …
fixed-rank non-symmetric matrix, we consider the optimization of a smooth cost function …
Universal matrix completion
S Bhojanapalli, P Jain - International Conference on …, 2014 - proceedings.mlr.press
The problem of low-rank matrix completion has recently generated a lot of interest leading to
several results that offer exact solutions to the problem. However, in order to do so, these …
several results that offer exact solutions to the problem. However, in order to do so, these …
A computational framework for influenza antigenic cartography
Influenza viruses have been responsible for large losses of lives around the world and
continue to present a great public health challenge. Antigenic characterization based on …
continue to present a great public health challenge. Antigenic characterization based on …
Fast exact matrix completion with finite samples
P Jain, P Netrapalli - Conference on Learning Theory, 2015 - proceedings.mlr.press
Matrix completion is the problem of recovering a low rank matrix by observing a small
fraction of its entries. A series of recent works (Keshavan 2012),(Jain et al. 2013) and (Hardt …
fraction of its entries. A series of recent works (Keshavan 2012),(Jain et al. 2013) and (Hardt …