Hongyi Wang
Hongyi Wang
Senior Researcher, Carnegie Mellon University
Geverifieerd e-mailadres voor andrew.cmu.edu - Homepage
Geciteerd door
Geciteerd door
Federated Learning with Matched Averaging
H Wang, M Yurochkin, Y Sun, D Papailiopoulos, Y Khazaeni
ICLR 2020 - International Conference on Learning Representations, 2020
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 31, 2018
Fedml: A research library and benchmark for federated machine learning
C He, S Li, J So, X Zeng, M Zhang, H Wang, X Wang, P Vepakomma, ...
arXiv preprint arXiv:2007.13518, 2020
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
Draco: Byzantine-resilient distributed training via redundant gradients
L Chen, H Wang, Z Charles, D Papailiopoulos
International Conference on Machine Learning, 903-912, 2018
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
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 32, 2019
Erasurehead: Distributed gradient descent without delays using approximate gradient coding
H Wang, Z Charles, D Papailiopoulos
arXiv preprint arXiv:1901.09671, 2019
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
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
Pufferfish: Communication-efficient models at no extra cost
H Wang, S Agarwal, D Papailiopoulos
Proceedings of Machine Learning and Systems 3, 365-386, 2021
The effect of network width on the performance of large-batch training
L Chen, H Wang, J Zhao, D Papailiopoulos, P Koutris
Advances in neural information processing systems 31, 2018
Efficient federated learning on knowledge graphs via privacy-preserving relation embedding aggregation
K Zhang, Y Wang, H Wang, L Huang, C Yang, L Sun
arXiv preprint arXiv:2203.09553, 2022
Rare Gems: Finding Lottery Tickets at Initialization
K Sreenivasan, J Sohn, L Yang, M Grinde, A Nagle, H Wang, K Lee, ...
NeurIPS 2022, 2022
Recognizing actions during tactile manipulations through force sensing
G Subramani, D Rakita, H Wang, J Black, M Zinn, M Gleicher
2017 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2017
Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach
H Guo, P Greengard, H Wang, A Gelman, Y Kim, EP Xing
arXiv preprint arXiv:2302.04228, 2023
MPCFormer: fast, performant and private Transformer inference with MPC
D Li, R Shao, H Wang, H Guo, EP Xing, H Zhang
arXiv preprint arXiv:2211.01452, 2022
Avoiding negative transfer on a focused task with deep multi-task reinforcement learning
YLAGS Liu, H Wang, Y Liang, A Gitter
AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness
D Li, H Wang, E Xing, H Zhang
NeurIPS 2022, 2022
Cuttlefish: Low-rank Model Training without All The Tuning
H Wang, S Agarwal, Y Tanaka, EP Xing, D Papailiopoulos
arXiv preprint arXiv:2305.02538, 2023
Het systeem kan de bewerking nu niet uitvoeren. Probeer het later opnieuw.
Artikelen 1–20