35 citations · 206 across the 44 of their papers we have counts for
5 papers · 1 filter
Non-Federated Multi-Task Split Learning for Heterogeneous Sources
Yilin Zheng, Atilla Eryilmaz
With the development of edge networks and mobile computing, the need to serve heterogeneous data sources at the network edge requires the design of new distributed machine learning…
Recurrent Natural Policy Gradient for POMDPs
Semih Cayci, Atilla Eryilmaz
Solving partially observable Markov decision processes (POMDPs) remains a fundamental challenge in reinforcement learning (RL), primarily due to the curse of dimensionality induced…
SwiftCache: Model-Based Learning for Dynamic Content Caching in CDNs
Bahman Abolhassani, Atilla Eryilmaz, Tom Hou
We introduce SwiftCache, a "fresh" learning-based caching framework designed for content distribution networks (CDNs) featuring distributed front-end local caches and a dynamic bac…
Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
Semih Cayci, Atilla Eryilmaz
We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices, trained with gradient descent in the supervised learning setting, and prove that gradient desce…
Optimal Push and Pull-Based Edge Caching For Dynamic Content
Bahman Abolhassani, John Tadrous, Atilla Eryilmaz +1
We introduce a framework and optimal `fresh' caching for a content distribution network (CDN) comprising a front-end local cache and a back-end database. The data content is dynami…