23 citations · 58 across the 52 of their papers we have counts for
6 papers · 1 filter
Robust and Resource-efficient Machine Learning Aided Viewport Prediction in Virtual Reality
Yuang Jiang, Konstantinos Poularakis, Diego Kiedanski +2
360-degree panoramic videos have gained considerable attention in recent years due to the rapid development of head-mounted displays (HMDs) and panoramic cameras. One major problem…
A Quantitative Theory of Bottleneck Structures for Data Networks
Jordi Ros-Giralt, Noah Amsel, Sruthi Yellamraju +5
The conventional view of the congestion control problem in data networks is based on the principle that a flow's performance is uniquely determined by the state of its bottleneck l…
An Overview of the Data-Loader Landscape: Comparative Performance Analysis
Iason Ofeidis, Diego Kiedanski, Leandros Tassiulas
Dataloaders, in charge of moving data from storage into GPUs while training machine learning models, might hold the key to drastically improving the performance of training jobs. R…
Accelerated Convex Optimization with Stochastic Gradients: Generalizing the Strong-Growth Condition
Víctor Valls, Shiqiang Wang, Yuang Jiang +1
This paper presents a sufficient condition for stochastic gradients not to slow down the convergence of Nesterov's accelerated gradient method. The new condition has the strong-gro…
Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecasting
Aosong Feng, Leandros Tassiulas
Traffic flow forecasting on graphs has real-world applications in many fields, such as transportation system and computer networks. Traffic forecasting can be highly challenging du…
KerGNNs: Interpretable Graph Neural Networks with Graph Kernels
Aosong Feng, Chenyu You, Shiqiang Wang +1
Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted com…