1k citations
- University of St AndrewsGB4 papers
- The University of TokyoJP3 papers
- Association for Computing MachineryUS1 paper
- Australian National UniversityAU1 paper
- Boston UniversityUS1 paper
- California Institute of TechnologyUS1 paper
- Dharma Drum Institute of Liberal ArtsTW1 paper
- Harvard UniversityUS1 paper
- Hasan Kalyoncu UniversityTR1 paper
- Huawei Technologies (China)CN1 paper
- Imperial College LondonGB1 paper
- Indian Institute of Technology JodhpurIN1 paper
4 papers · 1 filter
FedOptima: Optimizing Resource Utilization in Federated Learning
Zihan Zhang, Leon Wong, Blesson Varghese
Federated learning (FL) systems facilitate distributed machine learning across a server and multiple devices. However, FL systems have low resource utilization on servers and devic…
Mosaic: Composite Projection Pruning for Resource-efficient LLMs
Bailey J. Eccles, Leon Wong, Blesson Varghese
Extensive compute and memory requirements limit the deployment of large language models (LLMs) on any hardware. Compression methods, such as pruning, can reduce model size, which i…
Fastest Mixing Reversible Markov Chain: Clique Lifted Graphs and Subgraphs
Saber Jafarizadeh
Markov chains are one of the well-known tools for modeling and analyzing stochastic systems. At the same time, they are used for constructing random walks that can achieve a given…
Fastest mixing reversible Markov chain on friendship graph: Trade-off between transition probabilities among friends and convergence rate
Saber Jafarizadeh
A long-standing goal of social network research has been to alter the properties of network to achieve the desired outcome. In doing so, DeGroot's consensus model has served as the…