6 papers
Roomie: Interference-Aware Colocation for Efficient Model Serving
Youssouph Faye, Francescomaria Faticanti, Shubham Jain +1
As demand for DNN inference grows, GPU capacity is increasingly oversubscribed, forcing operators to colocate multiple models on the same device in both cloud and edge deployments.…
Characterizing the Impact of Active Queue Management on Speed Test Measurements
Siddhant Ray, Taveesh Sharma, Jonatas Marques +3
Present day speed test tools measure peak throughput, but often fail to capture the user-perceived responsiveness of a network connection under load. Recently, platforms such as ND…
Cruise Control: Dynamic Model Selection for ML-Based Network Traffic Analysis
Johann Hugon, Paul Schmitt, Anthony Busson +1
Modern networks increasingly rely on machine learning models for real-time insights, including traffic classification, application quality of experience inference, and intrusion de…
CATO: End-to-End Optimization of ML-Based Traffic Analysis Pipelines
Gerry Wan, Shinan Liu, Francesco Bronzino +2
Machine learning has shown tremendous potential for improving the capabilities of network traffic analysis applications, often outperforming simpler rule-based heuristics. However,…
Ironing the Graphs: Toward a Correct Geometric Analysis of Large-Scale Graphs
Saloua Naama, Kavé Salamatian, Francesco Bronzino
Graph embedding approaches attempt to project graphs into geometric entities, i.e, manifolds. The idea is that the geometric properties of the projected manifolds are helpful in th…
Optimal Flow Admission Control in Edge Computing via Safe Reinforcement Learning
A. Fox, F. De Pellegrini, F. Faticanti +2
With the uptake of intelligent data-driven applications, edge computing infrastructures necessitate a new generation of admission control algorithms to maximize system performance…