Prati
Sai Praneeth Karimireddy
Sai Praneeth Karimireddy
Ostala imenaSai Praneeth Reddy Karimireddy, Sai Praneeth Reddy
Postdoc, UC Berkeley
Potvrđena adresa e-pošte na berkeley.edu - Početna stranica
Naslov
Citirano
Citirano
Godina
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
SP Karimireddy, S Kale, M Mohri, SJ Reddi, SU Stich, AT Suresh
ICML 2020 - International Conference on Machine Learning, 2019
9812019
Error Feedback Fixes SignSGD and other Gradient Compression Schemes
SP Karimireddy, Q Rebjock, SU Stich, M Jaggi
ICML 2019 - International Conference on Machine Learning, 2019
3302019
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization
T Vogels, SP Karimireddy, M Jaggi
NeurIPS 2019 - Conference on Neural Information Processing Systems, 2019
1722019
The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication
SU Stich, SP Karimireddy
JMLR 2020 - Journal of Machine Learning Research, 2019
171*2019
A Field Guide to Federated Optimization
J Wang*, Z Charles*, Z Xu*, G Joshi*, HB McMahan, M Al-Shedivat, ...
arXiv preprint arXiv:2107.06917, 2021
1382021
Why are adaptive methods good for attention models?
J Zhang, SP Karimireddy, A Veit, S Kim, SJ Reddi, S Kumar, S Sra
NeurIPS 2020 - Conference on Neural Information Processing Systems, 2019
129*2019
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
SP Karimireddy, M Jaggi, S Kale, M Mohri, SJ Reddi, SU Stich, AT Suresh
NeurIPS 2021 - Conference on Neural Information Processing Systems, 2020
100*2020
Learning from History for Byzantine Robust Optimization
SP Karimireddy, L He, M Jaggi
ICML 2021 - International Conference on Machine Learning, 2020
582020
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing
SP Karimireddy*, L He*, M Jaggi
ICLR 2022 - International Conference on Learning Representations, 2021
44*2021
Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
T Lin, SP Karimireddy, SU Stich, M Jaggi
ICML 2021 - International Conference on Machine Learning, 2021
392021
Secure Byzantine-Robust Machine Learning
L He, SP Karimireddy, M Jaggi
arXiv preprint arXiv:2006.04747, 2020
322020
Global linear convergence of Newton's method without strong-convexity or Lipschitz gradients
SP Karimireddy, SU Stich, M Jaggi
NeurIPS 2019 Workshop 'Beyond First Order Methods in ML', 2018
292018
Accelerating Gradient Boosting Machine
H Lu*, SP Karimireddy*, N Ponomareva, V Mirrokni
AISTATS 2020 - International Conference on Artificial Intelligence and …, 2019
282019
Assignment techniques for crowdsourcing sensitive tasks
LE Celis, SP Reddy, IP Singh, S Vaya
Proceedings of the 19th ACM Conference on Computer-Supported Cooperative …, 2016
282016
PowerGossip: Practical Low-Rank Communication Compression in Decentralized Deep Learning
T Vogels, SP Karimireddy, M Jaggi
NeurIPS 2020 - Conference on Neural Information Processing Systems, 2020
25*2020
RelaySum for Decentralized Deep Learning on Heterogeneous Data
T Vogels*, L He*, A Koloskova, T Lin, SP Karimireddy, SU Stich, M Jaggi
NeurIPS 2021 - Conference on Neural Information Processing Systems, 2021
232021
On Matching Pursuit and Coordinate Descent
F Locatello, A Raj, SP Karimireddy, G Rätsch, B Schölkopf, SU Stich, ...
ICML 2018 - Proceedings of the 35th International Conference on Machine Learning, 2018
212018
Efficient Greedy Coordinate Descent for Composite Problems
SP Karimireddy*, A Koloskova*, SU Stich, M Jaggi
AISTATS 2019 - International Conference on Artificial Intelligence and …, 2018
192018
Multi-Broadcasting under the SINR Model
SP Karimireddy, DR Kowalski, S Vaya
PODC 2016 - Proceedings of the 2016 ACM Symposium on Principles of …, 2016
14*2016
Byzantine-Robust Decentralized Learning via Self-Centered Clipping
L He, SP Karimireddy, M Jaggi
arXiv preprint arXiv:2202.01545, 2022
112022
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–20