Sashank J. Reddi
Sashank J. Reddi
Research Scientist, Google Research
Verifierad e-postadress på cs.cmu.edu - Startsida
Titel
Citeras av
Citeras av
År
On the convergence of adam and beyond
SJ Reddi, S Kale, S Kumar
arXiv preprint arXiv:1904.09237, 2019
10942019
Stochastic variance reduction for nonconvex optimization
SJ Reddi, A Hefny, S Sra, B Poczos, A Smola
International conference on machine learning, 314-323, 2016
4122016
Fast Stochastic Methods for Nonsmooth Nonconvex Optimization
S J. Reddi, S Sra, B Poczos, A Smola
arXiv:1605.06900, 2016
157*2016
On variance reduction in stochastic gradient descent and its asynchronous variants
SJ Reddi, A Hefny, S Sra, B Poczos, AJ Smola
Advances in neural information processing systems, 2647-2655, 2015
1572015
Large batch optimization for deep learning: Training bert in 76 minutes
Y You, J Li, S Reddi, J Hseu, S Kumar, S Bhojanapalli, X Song, J Demmel, ...
arXiv preprint arXiv:1904.00962, 2019
1372019
Riemannian SVRG: Fast stochastic optimization on Riemannian manifolds
H Zhang, SJ Reddi, S Sra
arXiv preprint arXiv:1605.07147, 2016
1302016
On the decreasing power of kernel and distance based nonparametric hypothesis tests in high dimensions
A Ramdas, SJ Reddi, B Póczos, A Singh, L Wasserman
Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015
1082015
SCAFFOLD: Stochastic controlled averaging for federated learning
SP Karimireddy, S Kale, M Mohri, S Reddi, S Stich, AT Suresh
International Conference on Machine Learning, 5132-5143, 2020
1052020
Adaptive methods for nonconvex optimization
S Reddi, M Zaheer, D Sachan, S Kale, S Kumar
Proceeding of 32nd Conference on Neural Information Processing Systems (NIPS …, 2018
1012018
Stochastic frank-wolfe methods for nonconvex optimization
SJ Reddi, S Sra, B Póczos, A Smola
2016 54th Annual Allerton Conference on Communication, Control, and …, 2016
912016
AIDE: Fast and communication efficient distributed optimization
SJ Reddi, J Konečný, P Richtárik, B Póczós, A Smola
arXiv preprint arXiv:1608.06879, 2016
912016
A maximum likelihood approach for selecting sets of alternatives
AD Procaccia, SJ Reddi, N Shah
arXiv preprint arXiv:1210.4882, 2012
782012
Variance reduction in stochastic gradient Langevin dynamics
A Dubey, SJ Reddi, B Póczos, AJ Smola, EP Xing, SA Williamson
Advances in neural information processing systems 29, 1154, 2016
602016
A generic approach for escaping saddle points
S Reddi, M Zaheer, S Sra, B Poczos, F Bach, R Salakhutdinov, A Smola
International Conference on Artificial Intelligence and Statistics, 1233-1242, 2018
532018
Fast incremental method for smooth nonconvex optimization
SJ Reddi, S Sra, B Póczos, A Smola
2016 IEEE 55th Conference on Decision and Control (CDC), 1971-1977, 2016
53*2016
Adaptive federated optimization
S Reddi, Z Charles, M Zaheer, Z Garrett, K Rush, J Konečný, S Kumar, ...
arXiv preprint arXiv:2003.00295, 2020
512020
On the high dimensional power of a linear-time two sample test under mean-shift alternatives
S Reddi, A Ramdas, B Póczos, A Singh, L Wasserman
Artificial Intelligence and Statistics, 772-780, 2015
40*2015
Doubly robust covariate shift correction
S Reddi, B Poczos, A Smola
Proceedings of the AAAI Conference on Artificial Intelligence 29 (1), 2015
322015
Why adam beats sgd for attention models
J Zhang, S Praneeth Karimireddy, A Veit, S Kim, SJ Reddi, S Kumar, ...
arXiv e-prints, arXiv: 1912.03194, 2019
302019
Can gradient clipping mitigate label noise?
AK Menon, AS Rawat, SJ Reddi, S Kumar
272020
Systemet kan inte utföra åtgärden just nu. Försök igen senare.
Artiklar 1–20