Zachary Charles
Zachary Charles
AI Resident, Google
Verifierad e-postadress på google.com - Startsida
TitelCiteras avÅr
Draco: Byzantine-resilient distributed training via redundant gradients
L Chen, H Wang, Z Charles, D Papailiopoulos
arXiv preprint arXiv:1803.09877, 2018
44*2018
Atomo: Communication-efficient learning via atomic sparsification
H Wang, S Sievert, S Liu, Z Charles, D Papailiopoulos, S Wright
Advances in Neural Information Processing Systems, 9850-9861, 2018
372018
Approximate gradient coding via sparse random graphs
Z Charles, D Papailiopoulos, J Ellenberg
arXiv preprint arXiv:1711.06771, 2017
252017
Gradient coding using the stochastic block model
Z Charles, D Papailiopoulos
2018 IEEE International Symposium on Information Theory (ISIT), 1998-2002, 2018
16*2018
Stability and generalization of learning algorithms that converge to global optima
Z Charles, D Papailiopoulos
arXiv preprint arXiv:1710.08402, 2017
152017
Nonpositive eigenvalues of hollow, symmetric, nonnegative matrices
ZB Charles, M Farber, CR Johnson, L Kennedy-Shaffer
SIAM Journal on Matrix Analysis and Applications 34 (3), 1384-1400, 2013
82013
Sparse subspace clustering with missing and corrupted data
Z Charles, A Jalali, R Willett
2018 IEEE Data Science Workshop (DSW), 180-184, 2018
6*2018
Does Data Augmentation Lead to Positive Margin?
S Rajput, Z Feng, Z Charles, PL Loh, D Papailiopoulos
arXiv preprint arXiv:1905.03177, 2019
52019
DETOX: A redundancy-based framework for faster and more robust gradient aggregation
S Rajput, H Wang, Z Charles, D Papailiopoulos
Advances in Neural Information Processing Systems, 10320-10330, 2019
52019
A geometric perspective on the transferability of adversarial directions
Z Charles, H Rosenberg, D Papailiopoulos
arXiv preprint arXiv:1811.03531, 2018
52018
Distributions of the number of solutions to the network power flow equations
A Zachariah, Z Charles, N Boston, B Lesieutre
2018 IEEE International Symposium on Circuits and Systems (ISCAS), 1-5, 2018
52018
Sparse subspace clustering with missing and corrupted data. arXiv preprint
Z Charles, A Jalali, R Willett
arXiv preprint arXiv:1707.02461, 2017
52017
ErasureHead: Distributed gradient descent without delays using approximate gradient coding
H Wang, Z Charles, D Papailiopoulos
arXiv preprint arXiv:1901.09671, 2019
32019
Advances and open problems in federated learning
P Kairouz, HB McMahan, B Avent, A Bellet, M Bennis, AN Bhagoji, ...
arXiv preprint arXiv:1912.04977, 2019
22019
Exploiting algebraic structure in global optimization and the Belgian chocolate problem
Z Charles, N Boston
Journal of Global Optimization 72 (2), 241-254, 2018
12018
Efficiently finding all power flow solutions to tree networks
A Zachariah, Z Charles
2017 55th Annual Allerton Conference on Communication, Control, and …, 2017
12017
Nonpositive eigenvalues of the adjacency matrix and lower bounds for Laplacian eigenvalues
ZB Charles, M Farber, CR Johnson, L Kennedy-Shaffer
Discrete Mathematics 313 (13), 1441-1451, 2013
12013
The relation between the diagonal entries and the eigenvalues of a symmetric matrix, based upon the sign pattern of its off-diagonal entries
ZB Charles, M Farber, CR Johnson, L Kennedy-Shaffer
Linear Algebra and its Applications 438 (3), 1427-1445, 2013
12013
Improving the convergence of SGD through adaptive batch sizes
S Sievert, Z Charles
arXiv preprint arXiv:1910.08222, 2019
2019
Convergence and Margin of Adversarial Training on Separable Data
Z Charles, S Rajput, S Wright, D Papailiopoulos
arXiv preprint arXiv:1905.09209, 2019
2019
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20