Zobrazeno 1 - 10
of 143
pro vyhledávání: '"Toghani A"'
We study the problem of policy estimation for the Linear Quadratic Regulator (LQR) in discrete-time linear time-invariant uncertain dynamical systems. We propose a Moreau Envelope-based surrogate LQR cost, built from a finite set of realizations of t
Externí odkaz:
http://arxiv.org/abs/2403.17364
Federated learning (FL) is a distributed machine learning framework where the global model of a central server is trained via multiple collaborative steps by participating clients without sharing their data. While being a flexible framework, where th
Externí odkaz:
http://arxiv.org/abs/2306.11201
Meta-Reinforcement Learning (MRL) is a promising framework for training agents that can quickly adapt to new environments and tasks. In this work, we study the MRL problem under the policy gradient formulation, where we propose a novel algorithm that
Externí odkaz:
http://arxiv.org/abs/2305.12216
Autor:
Selvaraj, Muniyandi1 (AUTHOR), Toghani, AmirAli1 (AUTHOR), Pai, Hsuan1 (AUTHOR), Sugihara, Yu1 (AUTHOR), Kourelis, Jiorgos1 (AUTHOR), Yuen, Enoch Lok Him2 (AUTHOR), Ibrahim, Tarhan2 (AUTHOR), Zhao, He1 (AUTHOR), Xie, Rongrong1 (AUTHOR), Maqbool, Abbas1 (AUTHOR), De la Concepcion, Juan Carlos3 (AUTHOR), Banfield, Mark J.3 (AUTHOR), Derevnina, Lida1 (AUTHOR), Petre, Benjamin1 (AUTHOR), Lawson, David M.3 (AUTHOR), Bozkurt, Tolga O.2 (AUTHOR), Wu, Chih-Hang1 (AUTHOR), Kamoun, Sophien1 (AUTHOR) sophien.kamoun@tsl.ac.uk, Contreras, Mauricio P.1 (AUTHOR) sophien.kamoun@tsl.ac.uk
Publikováno v:
PLoS Biology. 10/18/2024, Vol. 22 Issue 10, p1-25. 25p.
We study the personalized federated learning problem under asynchronous updates. In this problem, each client seeks to obtain a personalized model that simultaneously outperforms local and global models. We consider two optimization-based frameworks
Externí odkaz:
http://arxiv.org/abs/2210.01176
Synchronous updates may compromise the efficiency of cross-device federated learning once the number of active clients increases. The \textit{FedBuff} algorithm (Nguyen et al., 2022) alleviates this problem by allowing asynchronous updates (staleness
Externí odkaz:
http://arxiv.org/abs/2210.01161
Publikováno v:
Bio-Protocol, Vol 14, Iss 13 (2024)
In recent years, the increase in genome sequencing across diverse plant species has provided a significant advantage for phylogenomics studies, allowing the analysis of one of the most diverse gene families in plants: nucleotide-binding leucine-rich
Externí odkaz:
https://doaj.org/article/24bb4059893e401b809208786e2bd8a4
We study the decentralized consensus and stochastic optimization problems with compressed communications over static directed graphs. We propose an iterative gradient-based algorithm that compresses messages according to a desired compression ratio.
Externí odkaz:
http://arxiv.org/abs/2204.08160
We propose a distributed Quantum State Tomography (QST) protocol, named Local Stochastic Factored Gradient Descent (Local SFGD), to learn the low-rank factor of a density matrix over a set of local machines. QST is the canonical procedure to characte
Externí odkaz:
http://arxiv.org/abs/2203.11579
Autor:
Schimek, Nels, Wood, Thomas R., Beck, David A.C., McKenna, Michael, Toghani, Ali, Nance, Elizabeth
Publikováno v:
In Biophysical Journal 19 November 2024 123(22):3935-3950