Related papers: Differentiated Services: an Experimental vs. Simul…
Backpressure routing and scheduling, with its throughput-optimal operation guarantee, is a promising technique to improve throughput in wireless multi-hop networks. Although backpressure is conceptually viewed as layered, the decisions of…
Edge computing requires the complex software interaction of geo-distributed, heterogeneous components. The growing research and industry interest in edge computing software systems has necessitated exploring ways of testing and evaluating…
Neural network-based methods for solving differential equations have been gaining traction. They work by improving the differential equation residuals of a neural network on a sample of points in each iteration. However, most of them employ…
Diffusion-based models have achieved notable empirical successes in reinforcement learning (RL) due to their expressiveness in modeling complex distributions. Despite existing methods being promising, the key challenge of extending existing…
In the past years, deep learning models have been successfully applied in several cognitive tasks. Originally inspired by neuroscience, these models are specific examples of differentiable programs. In this paper we define and motivate…
Simulating rare events, such as the transformation of a reactant into a product in a chemical reaction typically requires enhanced sampling techniques that rely on heuristically chosen collective variables (CVs). We propose using…
Distributed DNN inference is becoming increasingly important as the demand for intelligent services at the network edge grows. By leveraging the power of distributed computing, edge devices can perform complicated and resource-hungry…
The Data Distribution Service (DDS) is a widely used communication specification for real-time mission-critical systems that follow the principles of publish-subscribe middleware. DDS has an extensive set of quality of service (QoS)…
Automatic network management strategies have become paramount for meeting the needs of innovative real-time and data-intensive applications, such as in the Internet of Things. However, meeting the ever-growing and fluctuating demands for…
Robotic cutting of soft materials is critical for applications such as food processing, household automation, and surgical manipulation. As in other areas of robotics, simulators can facilitate controller verification, policy learning, and…
Deep learning, as a highly efficient method for metasurface inverse design, commonly use simulation data to train deep neural networks (DNNs) that can map desired functionalities to proper metasurface designs. However, the assumptions and…
Computer network tends to be subjected to the proliferation of mobile demands and increasingly multifarious, therefore it poses a great challenge to guarantee the quality of network service. By designing the model according to different…
We introduce DiffPhysCam, a differentiable camera simulator designed to support robotics and embodied AI applications by enabling gradient-based optimization in visual perception pipelines. Generating synthetic images that closely mimic…
Digital Twin technology facilitates the monitoring and online analysis of large-scale communication networks. Faster predictions of network performance thus become imperative, especially for analysing Quality of Service (QoS) parameters in…
Federated Learning (FL) is a paradigm for large-scale distributed learning which faces two key challenges: (i) efficient training from highly heterogeneous user data, and (ii) protecting the privacy of participating users. In this work, we…
Till today we dreamt of imperceptible delay in a network. The computer science research grows today faster than ever offering more and more services (computational representational, graphical, intelligent implication etc) to its user. But…
We present a differentiable simulation architecture for articulated rigid-body dynamics that enables the augmentation of analytical models with neural networks at any point of the computation. Through gradient-based optimization,…
Differentiable programming is a new programming paradigm which enables large scale optimization through automatic calculation of gradients also known as auto-differentiation. This concept emerges from deep learning, and has also been…
This paper shows an innovative solution for distributing dynamic sensor data by using distributed caches. Our proposal is based on the concepts of service modularization and virtualization of network nodes made available by the NetServ…
In artificial intelligence (AI), especially deep learning, data diversity and volume play a pivotal role in model development. However, training a robust deep learning model often faces challenges due to data privacy, regulations, and the…