Подписаться
Saurabh Agarwal
Saurabh Agarwal
Подтвержден адрес электронной почты в домене wisc.edu
Название
Процитировано
Процитировано
Год
Attack of the tails: Yes, you really can backdoor federated learning
H Wang, K Sreenivasan, S Rajput, H Vishwakarma, S Agarwal, J Sohn, ...
Advances in Neural Information Processing Systems 33, 16070-16084, 2020
1912020
Adaptive Gradient Communication via Critical Learning Regime Identification
S Agarwal, H Wang, K Lee, S Venkataraman, D Papailiopoulos
Proceedings of Machine Learning and Systems 3, 55-80, 2021
152021
On the utility of gradient compression in distributed training systems
S Agarwal, H Wang, S Venkataraman, D Papailiopoulos
Proceedings of Machine Learning and Systems 4, 652-672, 2022
122022
Pufferfish: Communication-efficient models at no extra cost
H Wang, S Agarwal, D Papailiopoulos
Proceedings of Machine Learning and Systems 3, 365-386, 2021
122021
AutoFreeze: Automatically Freezing Model Blocks to Accelerate Fine-tuning
Y Liu, S Agarwal, S Venkataraman
arXiv preprint arXiv:2102.01386, 2021
92021
BagPipe: Accelerating Deep Recommendation Model Training
S Agarwal, Z Zhang, S Venkataraman
arXiv preprint arXiv:2202.12429, 2022
2022
Method and system for efficient clustering of combined numeric and qualitative data records
S Agarwal, B Aravindakshan, B Sudarshan, H Chandrasekaran
US Patent 10,846,311, 2020
2020
Scalable K-Medoids via True Error Bound and Familywise Bandits
A Babu, S Agarwal, S Babu, H Chandrasekaran
arXiv preprint arXiv:1905.10979, 2019
2019
В данный момент система не может выполнить эту операцию. Повторите попытку позднее.
Статьи 1–8