Sahand Negahban
Sahand Negahban
Associate Professor, Yale University
Email verificata su - Home page
Citata da
Citata da
A Unified Framework for High-Dimensional Analysis of -Estimators with Decomposable Regularizers
SN Negahban, P Ravikumar, MJ Wainwright, B Yu
Estimation of (near) low-rank matrices with noise and high-dimensional scaling
S Negahban, MJ Wainwright
Restricted strong convexity and weighted matrix completion: Optimal bounds with noise
S Negahban, MJ Wainwright
The Journal of Machine Learning Research 13 (1), 1665-1697, 2012
Understanding adversarial training: Increasing local stability of supervised models through robust optimization
U Shaham, Y Yamada, S Negahban
Neurocomputing 307, 195-204, 2018
Iterative ranking from pair-wise comparisons
S Negahban, S Oh, D Shah
Advances in neural information processing systems 25, 2012
Fast global convergence rates of gradient methods for high-dimensional statistical recovery
A Agarwal, S Negahban, MJ Wainwright
Advances in Neural Information Processing Systems 23, 2010
Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions
A Agarwal, S Negahban, MJ Wainwright
Analysis of machine learning techniques for heart failure readmissions
BJ Mortazavi, NS Downing, EM Bucholz, K Dharmarajan, A Manhapra, ...
Circulation: Cardiovascular Quality and Outcomes 9 (6), 629-640, 2016
Simultaneous Support Recovery in High Dimensions: Benefits and Perils of Block-Regularization
SN Negahban, MJ Wainwright
IEEE Transactions on Information Theory 57 (6), 3841-3863, 2011
Using machine learning for discovery in synoptic survey imaging data
H Brink, JW Richards, D Poznanski, JS Bloom, J Rice, S Negahban, ...
Monthly Notices of the Royal Astronomical Society 435 (2), 1047-1060, 2013
Restricted strong convexity implies weak submodularity
ER Elenberg, R Khanna, AG Dimakis, S Negahban
The Annals of Statistics 46 (6B), 3539-3568, 2018
Scalable greedy feature selection via weak submodularity
R Khanna, E Elenberg, A Dimakis, S Negahban, J Ghosh
Artificial Intelligence and Statistics, 1560-1568, 2017
Feature selection using stochastic gates
Y Yamada, O Lindenbaum, S Negahban, Y Kluger
International Conference on Machine Learning, 10648-10659, 2020
Individualized rank aggregation using nuclear norm regularization
Y Lu, SN Negahban
2015 53rd Annual Allerton Conference on Communication, Control, and…, 2015
Comparison of machine learning methods with national cardiovascular data registry models for prediction of risk of bleeding after percutaneous coronary intervention
BJ Mortazavi, EM Bucholz, NR Desai, C Huang, JP Curtis, FA Masoudi, ...
JAMA network open 2 (7), e196835-e196835, 2019
Stochastic optimization and sparse statistical recovery: Optimal algorithms for high dimensions
A Agarwal, S Negahban, MJ Wainwright
Advances in Neural Information Processing Systems 25, 2012
Learning from comparisons and choices
S Negahban, S Oh, KK Thekumparampil, J Xu
The Journal of Machine Learning Research 19 (1), 1478-1572, 2018
Prediction of adverse events in patients undergoing major cardiovascular procedures
BJ Mortazavi, N Desai, J Zhang, A Coppi, F Warner, HM Krumholz, ...
IEEE journal of biomedical and health informatics 21 (6), 1719-1729, 2017
Warm-starting contextual bandits: Robustly combining supervised and bandit feedback
C Zhang, A Agarwal, H Daum III, J Langford, SN Negahban
arXiv preprint arXiv:1901.00301, 2019
Phase transitions for high-dimensional joint support recovery
S Negahban, MJ Wainwright
Advances in Neural Information Processing Systems 21, 2008
Il sistema al momento non pu eseguire l'operazione. Riprova pi tardi.
Articoli 1–20