Related papers: Data-Driven Approach for Accelerating Selective Ha…
Bulk synchronous parallel (BSP) is the de-facto paradigm for distributed DNN training in today's production clusters. However, due to the global synchronization nature, its performance can be significantly influenced by network bottlenecks…
Scaling multi-dimensional transformers to long sequences is indispensable across various domains. However, the challenges of large memory requirements and slow speeds of such sequences necessitate sequence parallelism. All existing…
A deep neural network (DNN) based power control method is proposed, which aims at solving the non-convex optimization problem of maximizing the sum rate of a multi-user interference channel. Towards this end, we first present PCNet, which…
Dual active bridge (DAB) converter is the key enabler in many popular applications such as wireless charging, electric vehicle and renewable energy. ZVS range and efficiency are two significant performance indicators for DAB converter. To…
In some practical learning tasks, such as traffic video analysis, the number of available training samples is restricted by different factors, such as limited communication bandwidth and computation power. Determinantal Point Process (DPP)…
Power system state estimation (PSSE) is commonly formulated as weighted least-square (WLS) algorithm and solved using iterative methods such as Gauss-Newton methods. However, iterative methods have become more sensitive to system operating…
This paper presents a new real-time intelligent optimization algorithm to minimize the voltage harmonics of a multilevel inverter. Hybrid Genetic algorithm /Particle swarm optimization algorithm is employed in a real-time simulation to…
Efficient parallel computing has become a pivotal element in advancing artificial intelligence. Yet, the deployment of Spiking Neural Networks (SNNs) in this domain is hampered by their inherent sequential computational dependency. This…
This paper presents a deep unfolding-supported coordinated multipoint beam pattern synthesis (DUCoMP-BPS) scheme to overcome the high complexity, poor adaptability, and limited scalability of traditional cell-free anti-jamming beamforming.…
Dimensionality reduction is a first step of many machine learning pipelines. Two popular approaches are principal component analysis, which projects onto a small number of well chosen but non-interpretable directions, and feature selection,…
In recent years, deep neural networks (DNN) have demonstrated significant business impact in large scale analysis and classification tasks such as speech recognition, visual object detection, pattern extraction, etc. Training of large DNNs,…
Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to…
Data augmentation is a crucial technique for improving model generalization and robustness, particularly in deep learning models where training data is limited. Although many augmentation methods have been developed for time series…
In this work, we first propose a parallel batch switching algorithm called Small-Batch Queue-Proportional Sampling (SB-QPS). Compared to other batch switching algorithms, SB-QPS significantly reduces the batch size without sacrificing the…
Probabilistic power flow (PPF) plays a critical role in power system analysis. However, the high computational burden makes it challenging for the practical implementation of PPF. This paper proposes a model-based deep learning approach to…
This thesis develops signal-processing algorithms and implementation schemes under constraints of minimal parallelism and memory space, with the goal of improving energy efficiency of low-power computing hardware. We propose (i) a…
Efficient parallelism is necessary for achieving low-latency, high-throughput inference with large language models (LLMs). Tensor parallelism (TP) is the state-of-the-art method for reducing LLM response latency, however GPU communications…
This paper presents a dynamic predictive sampling (DPS) based analog-to-digital converter (ADC) that provides a non-uniform sampling of input analog continuous-time signals. The processing unit generates a dynamic prediction of the input…
Stochastic computer simulations enable users to gain new insights into complex physical systems. Optimization is a common problem in this context: users seek to find model inputs that maximize the expected value of an objective function.…
Leveraging the overfitting property of deep neural networks (DNNs) is trending in video delivery systems to enhance video quality within bandwidth limits. Existing approaches transmit overfitted super-resolution (SR) model streams for…