One-shot federated learning: theoretical limits and algorithms to achieve them S Salehkaleybar, A Sharifnassab, SJ Golestani Journal of Machine Learning Research 22 (189), 1-47, 2021 | 29 | 2021 |
Connectivity analysis of one-dimensional ad hoc networks with arbitrary spatial distribution for variable and fixed number of nodes A Sharif-Nassab, F Ashtiani IEEE Transactions on Mobile Computing 11 (10), 1425-1435, 2011 | 26 | 2011 |
How to use real-valued sparse recovery algorithms for complex-valued sparse recovery? A Sharif-Nassab, M Kharratzadeh, M Babaie-Zadeh, C Jutten 2012 Proceedings of the 20th European Signal Processing Conference (EUSIPCO …, 2012 | 17 | 2012 |
Order optimal one-shot distributed learning A Sharifnassab, S Salehkaleybar, SJ Golestani Advances in Neural Information Processing Systems 32, 2019 | 14 | 2019 |
Distributed voting/ranking with optimal number of states per node S Salehkaleybar, A Sharif-Nassab, SJ Golestani IEEE Transactions on Signal and Information Processing over Networks 1 (4 …, 2015 | 13 | 2015 |
Bounds on over-parameterization for guaranteed existence of descent paths in shallow ReLU networks A Sharifnassab, S Salehkaleybar, SJ Golestani International conference on learning representations, 2019 | 9 | 2019 |
Fluctuation bounds for the max-weight policy with applications to state space collapse A Sharifnassab, JN Tsitsiklis, SJ Golestani Stochastic Systems 10 (3), 223-250, 2020 | 7 | 2020 |
Invariancy of sparse recovery algorithms M Kharratzadeh, A Sharifnassab, M Babaie-Zadeh IEEE Transactions on Information Theory 63 (6), 3333-3347, 2017 | 7 | 2017 |
Sensitivity to cumulative perturbations for a class of piecewise constant hybrid systems A Sharifnassab, JN Tsitsiklis, SJ Golestani IEEE Transactions on Automatic Control 65 (3), 1057-1072, 2019 | 4 | 2019 |
On the possibility of network scheduling with polynomial complexity and delay A Sharifnassab, SJ Golestani IEEE/ACM Transactions on Networking 25 (6), 3850-3862, 2017 | 4 | 2017 |
Method for distributed multi-choice voting/ranking S Salehkaleybar, A Sharifnassab, SJ Golestani US Patent 11,055,363, 2021 | 3 | 2021 |
Step-size Optimization for Continual Learning T Degris, K Javed, A Sharifnassab, Y Liu, R Sutton arXiv preprint arXiv:2401.17401, 2024 | 2 | 2024 |
Nonexpansive piecewise constant hybrid systems are conservative A Sharifnassab, JN Tsitsiklis, SJ Golestani arXiv preprint arXiv:1905.12361, 2019 | 2 | 2019 |
Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions A Sharifnassab, S Salehkaleybar, SJ Golestani IEEE Transactions on Information Theory, 2023 | 1* | 2023 |
When do trajectories have bounded sensitivity to cumulative perturbations? A Sharifnassab, SJ Golestani arXiv preprint arXiv:1905.11746, 2019 | 1 | 2019 |
Soft Preference Optimization: Aligning Language Models to Expert Distributions A Sharifnassab, S Ghiassian, S Salehkaleybar, S Kanoria, D Schuurmans arXiv preprint arXiv:2405.00747, 2024 | | 2024 |
MetaOptimize: A Framework for Optimizing Step Sizes and Other Meta-parameters A Sharifnassab, S Salehkaleybar, R Sutton arXiv preprint arXiv:2402.02342, 2024 | | 2024 |
Jumping Fluid Models and Delay Stability of Max-Weight Dynamics Under Heavy-Tailed Traffic A Sharifnassab, J Tsitsiklis Stochastic Systems 13 (4), 399-437, 2023 | | 2023 |
Toward efficient gradient-based value estimation A Sharifnassab, RS Sutton International Conference on Machine Learning, 30827-30849, 2023 | | 2023 |
SwiftTD: A Fast and Robust Algorithm for Temporal Difference Learning K Javed, A Sharifnassab, RS Sutton | | |