18 citations · 21 across the 4 of their papers we have counts for
4 papers
Toward Efficient Gradient-Based Value Estimation
Arsalan Sharifnassab, Richard Sutton
Gradient-based methods for value estimation in reinforcement learning have favorable stability properties, but they are typically much slower than Temporal Difference (TD) learning…
Jumping Fluid Models and Delay Stability of Max-Weight Dynamics under Heavy-Tailed Traffic
Arsalan Sharifnassab, John N. Tsitsiklis
We say that a random variable is - if moments of order are finite for some ; otherwise, we say that it is -. We study queueing networks tha…
Order Optimal Bounds for One-Shot Federated Learning over non-Convex Loss Functions
Arsalan Sharifnassab, Saber Salehkaleybar, S. Jamaloddin Golestani
We consider the problem of federated learning in a one-shot setting in which there are machines, each observing sample functions from an unknown distribution on non-convex…
One-Shot Federated Learning: Theoretical Limits and Algorithms to Achieve Them
Saber Salehkaleybar, Arsalan Sharifnassab, S. Jamaloddin Golestani
We consider distributed statistical optimization in one-shot setting, where there are machines each observing i.i.d. samples. Based on its observed samples, each machine se…