Related papers: Cross-Layer Effects on Training Neural Algorithms …
In queueing networks, it is well known that the throughput-optimal backpressure routing algorithm results in poor delay performance for light and moderate traffic loads. To improve delay performance, state-of-the-art backpressure routing…
Distributed Opportunistic Scheduling (DOS) techniques have been recently proposed to improve the throughput performance of wireless networks. With DOS, each station contends for the channel with a certain access probability. If a contention…
Communication overhead severely hinders the scalability of distributed machine learning systems. Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training.…
This paper investigates the cross-layer optimization of fast video delivery and caching for minimization of the overall video delivery time in a two-hop relaying network. The half-duplex relay nodes are equipped with both a cache and a…
One of the major challenges in training deep architectures for predictive tasks is the scarcity and cost of labeled training data. Active Learning (AL) is one way of addressing this challenge. In stream-based AL, observations are…
Emerging applications such as Deep Learning are often data-driven, thus traditional approaches based on auto-tuners are not performance effective across the wide range of inputs used in practice. In the present paper, we start an…
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features. As such, achieving high-performance execution for GNNs becomes crucially important. Prior works have proposed to explore the…
We investigate online convex optimization in non-stationary environments and choose dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible…
Training neural networks can be challenging, especially as the complexity of the problem increases. Despite using wider or deeper networks, training them can be a tedious process, especially if a wrong choice of the hyperparameter is made.…
Media streaming is the dominant application over wireless edge (access) networks. The increasing softwarization of such networks has led to efforts at intelligent control, wherein application-specific actions may be dynamically taken to…
Modern multi-access 5G+ networks provide mobile terminals with additional capacity, improving network stability and performance. However, in highly mobile environments such as vehicular networks, supporting multi-access connectivity remains…
The development of novel materials in recent years has been accelerated greatly by the use of computational modelling techniques aimed at elucidating the complex physics controlling microstructure formation in materials, the properties of…
Adaptive gradient methods such as Adam have been shown to be very effective for training deep neural networks (DNNs) by tracking the second moment of gradients to compute the individual learning rates. Differently from existing methods, we…
Non-stationary online learning has drawn much attention in recent years. In particular, dynamic regret and adaptive regret are proposed as two principled performance measures for online convex optimization in non-stationary environments. To…
Video streaming is in high demand by mobile users, as recent studies indicate. In cellular networks, however, the unreliable wireless channel leads to two major problems. Poor channel states degrade video quality and interrupt the playback…
Action recognition is an important research topic in computer vision. It is the basic work for visual understanding and has been applied in many fields. Since human actions can vary in different environments, it is difficult to infer…
Deep reinforcement learning in continuous domains focuses on learning control policies that map states to distributions over actions that ideally concentrate on the optimal choices in each step. In multi-agent navigation problems, the…
HTTP adaptive streaming (HAS) has emerged as a prevalent approach for over-the-top (OTT) video streaming services due to its ability to deliver a seamless user experience. A fundamental component of HAS is the bitrate ladder, which…
Existing approaches to resource allocation for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements. The present paper leverages online learning advances to facilitate stochastic resource…
Virtual reality has been gaining popularity in recent years caused by the proliferation of affordable consumer-grade devices such as Oculus Rift, HTC Vive, and Samsung VR. Amongst the various VR applications, 360{\deg} video streaming is…