Fred (Farbod) Roosta
Title
Cited by
Cited by
Year
Newton-type methods for non-convex optimization under inexact Hessian information
P Xu, F Roosta, MW Mahoney
Mathematical Programming, 1-36, 2017
942017
Sub-sampled Newton methods I: globally convergent algorithms
F Roosta-Khorasani, MW Mahoney
arXiv preprint arXiv:1601.04737, 2016
772016
Sub-sampled Newton methods II: Local convergence rates
F Roosta-Khorasani, MW Mahoney
arXiv preprint arXiv:1601.04738, 2016
722016
Sub-sampled Newton methods with non-uniform sampling
P Xu, J Yang, F Roosta, C Ré, MW Mahoney
Advances in Neural Information Processing Systems, 3000-3008, 2016
702016
Improved bounds on sample size for implicit matrix trace estimators
F Roosta-Khorasani, U Ascher
Foundations of Computational Mathematics 15 (5), 1187-1212, 2015
702015
Second-order optimization for non-convex machine learning: An empirical study
P Xu, F Roosta, MW Mahoney
Proceedings of the 2020 SIAM International Conference on Data Mining, 199-207, 2020
592020
Stochastic algorithms for inverse problems involving PDEs and many measurements
F Roosta-Khorasani, K van den Doel, U Ascher
SIAM Journal on Scientific Computing 36 (5), S3-S22, 2014
372014
Parallel local graph clustering
J Shun, F Roosta-Khorasani, K Fountoulakis, MW Mahoney
arXiv preprint arXiv:1604.07515, 2016
322016
GIANT: Globally improved approximate newton method for distributed optimization
S Wang, F Roosta-Khorasani, P Xu, MW Mahoney
Advances in Neural Information Processing Systems, 2338-2348, 2018
312018
Sub-sampled Newton methods
F Roosta-Khorasani, MW Mahoney
Mathematical Programming, 1-34, 2018
302018
Inexact non-convex Newton-type methods
Z Yao, P Xu, F Roosta-Khorasani, MW Mahoney
arXiv preprint arXiv:1802.06925, 2018
232018
Data completion and stochastic algorithms for PDE inversion problems with many measurements
F Roosta-Khorasani, K Van Den Doel, U Ascher
Electron. Trans. Numer. Anal 42, 177-196, 2014
212014
Variational perspective on local graph clustering
K Fountoulakis, F Roosta-Khorasani, J Shun, X Cheng, MW Mahoney
Mathematical Programming, 1-21, 2016
18*2016
Assessing stochastic algorithms for large scale nonlinear least squares problems using extremal probabilities of linear combinations of gamma random variables
F Roosta-Khorasani, GJ Székely, UM Ascher
SIAM/ASA Journal on Uncertainty Quantification 3 (1), 61-90, 2015
172015
Invariance of weight distributions in rectified MLPs
R Tsuchida, F Roosta-Khorasani, M Gallagher
arXiv preprint arXiv:1711.09090, 2017
102017
Union of Intersections (UoI) for interpretable data driven discovery and prediction
K Bouchard, A Bujan, F Roosta, S Ubaru, M Prabhat, A Snijders, JH Mao, ...
Advances in Neural Information Processing Systems, 1078-1086, 2017
102017
Randomized algorithms for solving large scale nonlinear least squares problems
F Roosta-Khorasani
University of British Columbia, 2015
92015
GPU accelerated sub-sampled Newton's method for convex classification problems
S Kylasa, F Roosta, MW Mahoney, A Grama
Proceedings of the 2019 SIAM International Conference on Data Mining, 702-710, 2019
8*2019
Newton-MR: Newton's Method Without Smoothness or Convexity
F Roosta, Y Liu, P Xu, MW Mahoney
arXiv preprint arXiv:1810.00303, 2018
82018
DINGO: Distributed Newton-Type Method for Gradient-Norm Optimization
R Crane, F Roosta
Advances in Neural Information Processing Systems, 9494-9504, 2019
52019
The system can't perform the operation now. Try again later.
Articles 1–20