Seguir
Seyed Mohammad Asghari
Seyed Mohammad Asghari
Research Engineer, DeepMind
Dirección de correo verificada de google.com
Título
Citado por
Citado por
Año
Epistemic neural networks
I Osband, Z Wen, SM Asghari, V Dwaracherla, M Ibrahimi, X Lu, ...
Advances in Neural Information Processing Systems 36, 2795-2823, 2023
1092023
Optimal local and remote controllers with unreliable uplink channels
SM Asghari, Y Ouyang, A Nayyar
IEEE Transactions on Automatic Control, 2018
432018
Optimal infinite horizon decentralized networked controllers with unreliable communication
Y Ouyang, SM Asghari, A Nayyar
IEEE Transactions on Automatic Control 66 (4), 1778-1785, 2020
242020
Optimal local and remote controllers with unreliable communication
Y Ouyang, SM Asghari, A Nayyar
2016 IEEE 55th conference on decision and control (CDC), 6024-6029, 2016
242016
Approximate thompson sampling via epistemic neural networks
I Osband, Z Wen, SM Asghari, V Dwaracherla, M Ibrahimi, X Lu, ...
Uncertainty in Artificial Intelligence, 1586-1595, 2023
202023
The neural testbed: Evaluating joint predictions
I Osband, Z Wen, SM Asghari, V Dwaracherla, X Lu, M Ibrahimi, ...
Advances in Neural Information Processing Systems 35, 12554-12565, 2022
202022
Ensembles for uncertainty estimation: Benefits of prior functions and bootstrapping
V Dwaracherla, Z Wen, I Osband, X Lu, SM Asghari, B Van Roy
arXiv preprint arXiv:2206.03633, 2022
142022
Dynamic teams and decentralized control problems with substitutable actions
SM Asghari, A Nayyar
IEEE Transactions on Automatic Control 62 (10), 5302-5309, 2016
132016
A self-organizing approach to malicious detection in leader-based mobile ad-hoc networks
SM Asghari, M Noormohammadpour, MJ Salehi, BH Khalaj, H Bagheri, ...
Wireless Days (WD), 2013 IFIP, 1-3, 2013
13*2013
Efficient exploration for llms
V Dwaracherla, SM Asghari, B Hao, B Van Roy
arXiv preprint arXiv:2402.00396, 2024
122024
Regret bounds for decentralized learning in cooperative multi-agent dynamical systems
SM Asghari, Y Ouyang, A Nayyar
Conference on Uncertainty in Artificial Intelligence, 121-130, 2020
122020
Optimal coded multicast in cache networks with arbitrary content placement
SM Asghari, Y Ouyang, A Nayyar, AS Avestimehr
2018 IEEE International Conference on Communications (ICC), 1-6, 2018
122018
Evaluating predictive distributions: Does Bayesian deep learning work?
I Osband, Z Wen, SM Asghari, X Lu, M Ibrahimi, V Dwaracherla, ...
102021
Fine-tuning language models via epistemic neural networks
I Osband, SM Asghari, B Van Roy, N McAleese, J Aslanides, G Irving
arXiv preprint arXiv:2211.01568, 2022
92022
An approximation algorithm for optimal clique cover delivery in coded caching
SM Asghari, Y Ouyang, A Nayyar, AS Avestimehr
IEEE Transactions on Communications 67 (7), 4683-4695, 2019
9*2019
Optimal local and remote controllers with unreliable communication: the infinite horizon case
Y Ouyang, SM Asghari, A Nayyar
2018 Annual American Control Conference (ACC), 6634-6639, 2018
92018
Decentralized control problems with substitutable actions
SM Asghari, A Nayyar
2015 54th IEEE Conference on Decision and Control (CDC), 5302-5307, 2015
92015
Stochastic teams with randomized information structures
Y Ouyang, SM Asghari, A Nayyar
2017 IEEE 56th Annual Conference on Decision and Control (CDC), 4733-4738, 2017
82017
Evaluating high-order predictive distributions in deep learning
I Osband, Z Wen, SM Asghari, V Dwaracherla, X Lu, B Van Roy
Uncertainty in Artificial Intelligence, 1552-1560, 2022
72022
An incentive-based leader selection mechanism for mobile ad-hoc networks (MANETs)
SM Asghari, MJ Salehi, M Noormohammadpour, BH Khalaj, H Bagheri, ...
Wireless Days (WD), 2013 IFIP, 1-6, 2013
3*2013
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20