Folgen
Sashank J. Reddi
Sashank J. Reddi
Sonstige NamenSashank Reddi, Sashank Jakkam Reddi
Research Scientist, Google Research
Bestätigte E-Mail-Adresse bei cs.cmu.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
On the convergence of adam and beyond
SJ Reddi, S Kale, S Kumar
arXiv preprint arXiv:1904.09237, 2019
25212019
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
16132020
Adaptive federated optimization
S Reddi, Z Charles, M Zaheer, Z Garrett, K Rush, J Konečný, S Kumar, ...
arXiv preprint arXiv:2003.00295, 2020
8722020
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
7392019
Stochastic variance reduction for nonconvex optimization
SJ Reddi, A Hefny, S Sra, B Poczos, A Smola
International conference on machine learning, 314-323, 2016
5962016
Adaptive methods for nonconvex optimization
M Zaheer, S Reddi, D Sachan, S Kale, S Kumar
Advances in neural information processing systems 31, 2018
3602018
Riemannian SVRG: Fast stochastic optimization on Riemannian manifolds
H Zhang, S J Reddi, S Sra
Advances in Neural Information Processing Systems 29, 2016
2442016
Fast Stochastic Methods for Nonsmooth Nonconvex Optimization
S J. Reddi, S Sra, B Poczos, A Smola
arXiv:1605.06900, 2016
232*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
1952015
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
1692015
Are transformers universal approximators of sequence-to-sequence functions?
C Yun, S Bhojanapalli, AS Rawat, SJ Reddi, S Kumar
arXiv preprint arXiv:1912.10077, 2019
1662019
Aide: Fast and communication efficient distributed optimization
SJ Reddi, J Konečný, P Richtárik, B Póczós, A Smola
arXiv preprint arXiv:1608.06879, 2016
1582016
International Conference on Learning Representations
SJ Reddi, S Kale, S Kumar
ICLR, New Orleans, Louisiana, 2018
1552018
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
1542016
Mime: Mimicking centralized stochastic algorithms in federated learning
SP Karimireddy, M Jaggi, S Kale, M Mohri, SJ Reddi, SU Stich, AT Suresh
arXiv preprint arXiv:2008.03606, 2020
1432020
A field guide to federated optimization
J Wang, Z Charles, Z Xu, G Joshi, HB McMahan, M Al-Shedivat, G Andrew, ...
arXiv preprint arXiv:2107.06917, 2021
1402021
Why are adaptive methods good for attention models?
J Zhang, SP Karimireddy, A Veit, S Kim, S Reddi, S Kumar, S Sra
Advances in Neural Information Processing Systems 33, 15383-15393, 2020
1232020
Can gradient clipping mitigate label noise?
AK Menon, AS Rawat, SJ Reddi, S Kumar
International Conference on Learning Representations, 2019
1182019
Adaclip: Adaptive clipping for private sgd
V Pichapati, AT Suresh, FX Yu, SJ Reddi, S Kumar
arXiv preprint arXiv:1908.07643, 2019
982019
Variance reduction in stochastic gradient Langevin dynamics
KA Dubey, S J Reddi, SA Williamson, B Poczos, AJ Smola, EP Xing
Advances in neural information processing systems 29, 2016
912016
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20