Seguir
Dong Yin
Dong Yin
Research Scientist, DeepMind
Email confirmado em google.com - Página inicial
Título
Citado por
Citado por
Ano
Byzantine-robust distributed learning: Towards optimal statistical rates
D Yin, Y Chen, R Kannan, P Bartlett
International Conference on Machine Learning, 5650-5659, 2018
6732018
A fourier perspective on model robustness in computer vision
D Yin, R Gontijo Lopes, J Shlens, ED Cubuk, J Gilmer
Advances in Neural Information Processing Systems 32, 13276-13286, 2019
3012019
An efficient framework for clustered federated learning
A Ghosh, J Chung, D Yin, K Ramchandran
IEEE Transactions on Information Theory 68 (12), 8076-8091, 2022
2842022
Rademacher complexity for adversarially robust generalization
D Yin, R Kannan, P Bartlett
International Conference on Machine Learning, 7085-7094, 2019
2072019
Improving robustness without sacrificing accuracy with patch gaussian augmentation
RG Lopes, D Yin, B Poole, J Gilmer, ED Cubuk
arXiv preprint arXiv:1906.02611, 2019
1452019
Robust federated learning in a heterogeneous environment
A Ghosh, J Hong, D Yin, K Ramchandran
arXiv preprint arXiv:1906.06629, 2019
1292019
Gradient diversity: a key ingredient for scalable distributed learning
D Yin, A Pananjady, M Lam, D Papailiopoulos, K Ramchandran, P Bartlett
International Conference on Artificial Intelligence and Statistics, 1998-2007, 2018
1192018
Defending against saddle point attack in Byzantine-robust distributed learning
D Yin, Y Chen, R Kannan, P Bartlett
International Conference on Machine Learning, 7074-7084, 2019
852019
Phasecode: Fast and efficient compressive phase retrieval based on sparse-graph codes
R Pedarsani, D Yin, K Lee, K Ramchandran
IEEE Transactions on Information Theory 63 (6), 3663-3691, 2017
652017
Stochastic Gradient and Langevin Processes
X Cheng, D Yin, P Bartlett, M Jordan
arXiv preprint arXiv:1907.03215, 2019
30*2019
Learning mixtures of sparse linear regressions using sparse graph codes
D Yin, R Pedarsani, Y Chen, K Ramchandran
IEEE Transactions on Information Theory 65 (3), 1430-1451, 2019
292019
Sub-linear time support recovery for compressed sensing using sparse-graph codes
X Li, D Yin, S Pawar, R Pedarsani, K Ramchandran
IEEE Transactions on Information Theory 65 (10), 6580-6619, 2019
282019
Sub-linear time support recovery for compressed sensing using sparse-graph codes
X Li, D Yin, S Pawar, R Pedarsani, K Ramchandran
IEEE Transactions on Information Theory 65 (10), 6580-6619, 2019
282019
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
D Yin, M Farajtabar, A Li, N Levine, A Mott
arXiv preprint arXiv:2006.10974, 2020
27*2020
Architecture matters in continual learning
SI Mirzadeh, A Chaudhry, D Yin, T Nguyen, R Pascanu, D Gorur, ...
arXiv preprint arXiv:2202.00275, 2022
182022
The Effectiveness of Memory Replay in Large Scale Continual Learning
Y Balaji, M Farajtabar, D Yin, A Mott, A Li
arXiv preprint arXiv:2010.02418, 2020
182020
Distributed sequence memory of multidimensional inputs in recurrent networks
AS Charles, D Yin, CJ Rozell
The Journal of Machine Learning Research 18 (1), 181-217, 2017
162017
Wide neural networks forget less catastrophically
SI Mirzadeh, A Chaudhry, D Yin, H Hu, R Pascanu, D Gorur, M Farajtabar
International Conference on Machine Learning, 15699-15717, 2022
132022
Fast and robust compressive phase retrieval with sparse-graph codes
D Yin, K Lee, R Pedarsani, K Ramchandran
2015 IEEE International Symposium on Information Theory (ISIT), 2583-2587, 2015
132015
Efficient local planning with linear function approximation
D Yin, B Hao, Y Abbasi-Yadkori, N Lazić, C Szepesvári
International Conference on Algorithmic Learning Theory, 1165-1192, 2022
92022
O sistema não pode efectuar a operação agora. Tente mais tarde.
Artigos 1–20