Farbod Roosta-Khorasani

Publication Activity (10 Years)

Years Active: 2013-2019
Publications (10 Years): 18

Top Topics

Problems Involving

Convergence Rate

Graph Clustering

Top Venues

Publications

Farbod Roosta-Khorasani, Michael W. Mahoney
Sub-sampled Newton methods. Math. Program. 174 (1-2) (2019)
Kimon Fountoulakis, Farbod Roosta-Khorasani, Julian Shun, Xiang Cheng, Michael W. Mahoney
Variational perspective on local graph clustering. Math. Program. 174 (1-2) (2019)
Russell Tsuchida, Farbod Roosta-Khorasani, Marcus Gallagher
Invariance of Weight Distributions in Rectified MLPs. ICML (2018)
Sudhir B. Kylasa, Farbod Roosta-Khorasani, Michael W. Mahoney, Ananth Grama
GPU Accelerated Sub-Sampled Newton\textsf{'}s Method. CoRR (2018)
Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney
GIANT: Globally Improved Approximate Newton Method for Distributed Optimization. NeurIPS (2018)
Chih-Hao Fang, Sudhir B. Kylasa, Farbod Roosta-Khorasani, Michael W. Mahoney, Ananth Grama
Distributed Second-order Convex Optimization. CoRR (2018)
Keith D. Levin, Farbod Roosta-Khorasani, Michael W. Mahoney, Carey E. Priebe
Out-of-sample extension of graph adjacency spectral embedding. ICML (2018)
Russell Tsuchida, Farbod Roosta-Khorasani, Marcus Gallagher
Invariance of Weight Distributions in Rectified MLPs. CoRR (2017)
Peng Xu, Farbod Roosta-Khorasani, Michael W. Mahoney
Second-Order Optimization for Non-Convex Machine Learning: An Empirical Study. CoRR (2017)
Peng Xu, Farbod Roosta-Khorasani, Michael W. Mahoney
Newton-Type Methods for Non-Convex Optimization Under Inexact Hessian Information. CoRR (2017)
Kristofer E. Bouchard, Alejandro F. Bujan, Farbod Roosta-Khorasani, Shashanka Ubaru, Prabhat, Antoine Snijders, Jian-Hua Mao, Edward F. Chang, Michael W. Mahoney, Sharmodeep Bhattacharyya
Union of Intersections (UoI) for Interpretable Data Driven Discovery and Prediction. NIPS (2017)
Shusen Wang, Farbod Roosta-Khorasani, Peng Xu, Michael W. Mahoney
GIANT: Globally Improved Approximate Newton Method for Distributed Optimization. CoRR (2017)
Peng Xu, Jiyan Yang, Farbod Roosta-Khorasani, Christopher Ré, Michael W. Mahoney
Sub-sampled Newton Methods with Non-uniform Sampling. NIPS (2016)
Xiang Cheng, Farbod Roosta-Khorasani, Peter L. Bartlett, Michael W. Mahoney
FLAG: Fast Linearly-Coupled Adaptive Gradient Method. CoRR (2016)
Farbod Roosta-Khorasani, Michael W. Mahoney
Sub-Sampled Newton Methods II: Local Convergence Rates. CoRR (2016)
Julian Shun, Farbod Roosta-Khorasani, Kimon Fountoulakis, Michael W. Mahoney
Parallel Local Graph Clustering. CoRR (2016)
Julian Shun, Farbod Roosta-Khorasani, Kimon Fountoulakis, Michael W. Mahoney
Parallel Local Graph Clustering. Proc. VLDB Endow. 9 (12) (2016)
Farbod Roosta-Khorasani, Michael W. Mahoney
Sub-Sampled Newton Methods I: Globally Convergent Algorithms. CoRR (2016)
Farbod Roosta-Khorasani, Gábor J. Székely, Uri M. Ascher
Assessing Stochastic Algorithms for Large Scale Nonlinear Least Squares Problems Using Extremal Probabilities of Linear Combinations of Gamma Random Variables. SIAM/ASA J. Uncertain. Quantification 3 (1) (2015)
Farbod Roosta-Khorasani, Uri M. Ascher
Improved Bounds on Sample Size for Implicit Matrix Trace Estimators. Found. Comput. Math. 15 (5) (2015)
Farbod Roosta-Khorasani, Gábor J. Székely, Uri M. Ascher
Assessing stochastic algorithms for large scale nonlinear least squares problems using extremal probabilities of linear combinations of gamma random variables. CoRR (2014)
Farbod Roosta-Khorasani, Kees van den Doel, Uri M. Ascher
Stochastic Algorithms for Inverse Problems Involving PDEs and many Measurements. SIAM J. Sci. Comput. 36 (5) (2014)
Uri M. Ascher, Farbod Roosta-Khorasani
Algorithms that satisfy a stopping criterion, probably. CoRR (2014)
Farbod Roosta-Khorasani, Kees van den Doel, Uri M. Ascher
Data completion and stochastic algorithms for PDE inversion problems with many measurements. CoRR (2013)
Farbod Roosta-Khorasani, Uri M. Ascher
Improved bounds on sample size for implicit matrix trace estimators. CoRR (2013)