Paul Grigas
Paul Grigas
Assistant Professor, UC Berkeley
Verifierad e-postadress på berkeley.edu - Startsida
Titel
Citeras av
Citeras av
År
New analysis and results for the Frank–Wolfe method
RM Freund, P Grigas
Mathematical Programming 155 (1-2), 199-230, 2016
116*2016
An Extended Frank--Wolfe Method with “In-Face” Directions, and Its Application to Low-Rank Matrix Completion
RM Freund, P Grigas, R Mazumder
SIAM Journal on optimization 27 (1), 319-346, 2017
532017
Smart "Predict, then Optimize"
AN Elmachtoub, P Grigas
arXiv preprint arXiv:1710.08005, 2017
50*2017
A new perspective on boosting in linear regression via subgradient optimization and relatives
RM Freund, P Grigas, R Mazumder
The Annals of Statistics 45 (6), 2328-2364, 2017
182017
Adaboost and forward stagewise regression are first-order convex optimization methods
RM Freund, P Grigas, R Mazumder
arXiv preprint arXiv:1307.1192, 2013
52013
Generalization bounds in the predict-then-optimize framework
O El Balghiti, AN Elmachtoub, P Grigas, A Tewari
Advances in Neural Information Processing Systems, 14412-14421, 2019
42019
Profit Maximization for Online Advertising Demand-Side Platforms
P Grigas, A Lobos, Z Wen, K Lee
Proceedings of the ADKDD'17, 1-7, 2017
32017
Incremental Forward Stagewise Regression: Computational Complexity and Connections to LASSO
RM Freund, P Grigas, R Mazumder
International Workshop on advances in Regularization, Optimization, Kernel …, 2013
32013
Optimal bidding, allocation and budget spending for a demand side platform under many auction types
A Lobos, P Grigas, Z Wen, K Lee
arXiv preprint arXiv:1805.11645, 2018
22018
Stochastic In-Face Frank-Wolfe Methods for Non-Convex Optimization and Sparse Neural Network Training
P Grigas, A Lobos, N Vermeersch
arXiv preprint arXiv:1906.03580, 2019
12019
Condition number analysis of logistic regression, and its implications for standard first-order solution methods
RM Freund, P Grigas, R Mazumder
arXiv preprint arXiv:1810.08727, 2018
12018
Methods for convex optimization and statistical learning
PPE Grigas
Massachusetts Institute of Technology, 2016
12016
New Methods for Regularization Path Optimization via Differential Equations
H Liu, P Grigas
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–13