Challenges of big data analysis

J Fan, F Han, H Liu - National science review, 2014‏ - academic.oup.com
Big Data bring new opportunities to modern society and challenges to data scientists. On the
one hand, Big Data hold great promises for discovering subtle population patterns and …

Transformers as statisticians: Provable in-context learning with in-context algorithm selection

Y Bai, F Chen, H Wang, C ** from saddle points—online stochastic gradient for tensor decomposition
R Ge, F Huang, C **, Y Yuan - Conference on learning …, 2015‏ - proceedings.mlr.press
We analyze stochastic gradient descent for optimizing non-convex functions. In many cases
for non-convex functions the goal is to find a reasonable local minimum, and the main …

Phase retrieval via Wirtinger flow: Theory and algorithms

EJ Candes, X Li… - IEEE Transactions on …, 2015‏ - ieeexplore.ieee.org
We study the problem of recovering the phase from magnitude measurements; specifically,
we wish to reconstruct a complex-valued signal about which we have phaseless samples of …

Structured regularizers for high-dimensional problems: Statistical and computational issues

MJ Wainwright - Annual Review of Statistics and Its Application, 2014‏ - annualreviews.org
Regularization is a widely used technique throughout statistics, machine learning, and
applied mathematics. Modern applications in science and engineering lead to massive and …

Guaranteed matrix completion via non-convex factorization

R Sun, ZQ Luo - IEEE Transactions on Information Theory, 2016‏ - ieeexplore.ieee.org
Matrix factorization is a popular approach for large-scale matrix completion. The optimization
formulation based on matrix factorization, even with huge size, can be solved very efficiently …

Regularized M-estimators with nonconvexity: Statistical and algorithmic theory for local optima

PL Loh, MJ Wainwright - The Journal of Machine Learning Research, 2015‏ - dl.acm.org
We provide novel theoretical results regarding local optima of regularized M-estimators,
allowing for nonconvexity in both loss and penalty functions. Under restricted strong …