Related papers: Efficient Synaptic Delay Implementation in Digital…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…
This paper presents fault-tolerant asynchronous Stochastic Gradient Descent (SGD) algorithms. SGD is widely used for approximating the minimum of a cost function $Q$, as a core part of optimization and learning algorithms. Our algorithms…
Energy management is a crucial challenge in wireless sensor networks. To date, many techniques have been proposed to reduce energy consumption. Duty cycle methods reduce the energy consumption of wireless sensor networks since energy…
We present a Spiking Neural Network (SNN) model that incorporates learnable synaptic delays through two approaches: per-synapse delay learning via Dilated Convolutions with Learnable Spacings (DCLS) and a dynamic pruning strategy that also…
Inspired by several delay-bounded mission-critical applications, this paper investigates chase-combining-based hybrid automatic repeat request (CC-HARQ) protocols to achieve high reliability in delay-constrained applications. A salient…
The use of deep learning has grown at an exponential rate, giving rise to numerous specialized hardware and software systems for deep learning. Because the design space of deep learning software stacks and hardware accelerators is diverse…
We propose a new algorithm to simplify the controller development for distributed robotic systems subject to external observations, disturbances, and communication delays. Unlike prior approaches that propose specialized solutions to…
To train modern large DNN models, pipeline parallelism has recently emerged, which distributes the model across GPUs and enables different devices to process different microbatches in pipeline. Earlier pipeline designs allow multiple…
Spiking Neural Networks (SNNs) have emerged as a biologically inspired alternative to conventional deep networks, offering event-driven and energy-efficient computation. However, their throughput remains constrained by the serial update of…
The Transformer architecture, underpinned by the Multi-Head Attention (MHA) mechanism, has become the de facto standard for state-of-the-art models in artificial intelligence. However, the quadratic computational complexity of MHA with…
We propose an asynchronous, decentralized algorithm for consensus optimization. The algorithm runs over a network in which the agents communicate with their neighbors and perform local computation. In the proposed algorithm, each agent can…
The Channel Quality Indicator (CQI) is a fundamental component of channel state information (CSI) that enables adaptive modulation and coding by selecting the optimal modulation and coding scheme to meet a target block error rate. While…
Delays endanger safety of autonomous systems operating in a rapidly changing environment, such as nondeterministic surrounding traffic participants in autonomous driving and high-speed racing. Unfortunately, delays are typically not…
A key motivation in the development of Distributed Model Predictive Control (DMPC) is to accelerate centralized Model Predictive Control (MPC) for large-scale systems. DMPC has the prospect of scaling well by parallelizing computations…
To bridge the gap between limited hardware access and the huge demand for experiments for Noisy Intermediate-Scale Quantum (NISQ) computing system study, a simulator which can capture the modeling of both the quantum processor and its…
Decentralized learning has emerged as a powerful approach for handling large datasets across multiple machines in a communication-efficient manner. However, such methods often face scalability limitations, as increasing the number of…
Caching at the base stations (BSs) has been widely adopted to reduce the delivery delay and alleviate the backhaul traffic between BSs and the core network. In this paper, we consider a collaborative content caching scheme among BSs in…
A new congestion and delay control algorithm named QUIC Delay Control (QUIC-DC) is proposed for controlling not only congestion but also the queueing delay encountered along the forward communication path. The core idea is to estimate the…
Dynamic resource allocation to parallel queues is a cornerstone of network scheduling, yet classical solutions often fail when accounting for the overhead of switching delays to queues with superior link conditions. In particular, system…
We show how the recent extension of spectral submanifold (SSM) theory to delay differential equations (DDEs) enables data-driven model reduction of nonlinear delay systems. First, using a scalar DDE with a single discrete delay, we compare…