63 citations · 323 across the 46 of their papers we have counts for
8 papers · 1 filter
Adaptive Federated Learning with Auto-Tuned Clients
Junhyung Lyle Kim, Mohammad Taha Toghani, César A. Uribe +1
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…
On First-Order Meta-Reinforcement Learning with Moreau Envelopes
Mohammad Taha Toghani, Sebastian Perez-Salazar, César A. Uribe
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 th…
Unbounded Gradients in Federated Learning with Buffered Asynchronous Aggregation
Mohammad Taha Toghani, César A. Uribe
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., 202…
PersA-FL: Personalized Asynchronous Federated Learning
Mohammad Taha Toghani, Soomin Lee, César A. Uribe
We study the personalized federated learning problem under asynchronous updates. In this problem, each client seeks to obtain a personalized model that simultaneously outperforms l…
The Role of Local Steps in Local SGD
Tiancheng Qin, S. Rasoul Etesami, César A. Uribe
We consider the distributed stochastic optimization problem where agents want to minimize a global function given by the sum of agents' local functions, and focus on the hetero…
Faster Convergence of Local SGD for Over-Parameterized Models
Tiancheng Qin, S. Rasoul Etesami, César A. Uribe
Modern machine learning architectures are often highly expressive. They are usually over-parameterized and can interpolate the data by driving the empirical loss close to zero. We…
Communication-efficient Distributed Cooperative Learning with Compressed Beliefs
Mohammad Taha Toghani, César A. Uribe
We study the problem of distributed cooperative learning, where a group of agents seeks to agree on a set of hypotheses that best describes a sequence of private observations. In t…
Communication-efficient Decentralized Local SGD over Undirected Networks
Tiancheng Qin, S. Rasoul Etesami, César A. Uribe
We consider the distributed learning problem where a network of agents seeks to minimize a global function . Agents have access to through noisy gradients, and they can…