Related papers: Near-Optimal Wafer-Scale Reduce
Distribution System State Estimation (DSSE) is becoming increasingly important with the integration of Distributed Energy Resources (DERs) and the active operation of distribution networks (DNs), but it remains challenging due to the…
Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…
Deep Learning (DL) training platforms are built by interconnecting multiple DL accelerators (e.g., GPU/TPU) via fast, customized interconnects with 100s of gigabytes (GBs) of bandwidth. However, as we identify in this work, driving this…
Distributed stochastic gradient descent (SGD) approach has been widely used in large-scale deep learning, and the gradient collective method is vital to ensure the training scalability of the distributed deep learning system. Collective…
Kernel machines often yield superior predictive performance on various tasks; however, they suffer from severe computational challenges. In this paper, we show how to overcome the important challenge of speeding up kernel machines. In…
Improving throughput for cell-edge users through coordinated resource allocation has been a long-standing driver of research in wireless cellular networks. While a variety of wireless resource management problems focus on sum utility,…
Recently, businesses have started using MapReduce as a popular computation framework for processing large amount of data, such as spam detection, and different data mining tasks, in both public and private clouds. Two of the challenging…
Training large language models (LLMs) imposes extreme demands on computation, memory capacity, and interconnect bandwidth, driven by their ever-increasing parameter scales and intensive data movement. Wafer-scale integration offers a…
This correspondence studies the wireless powered over-the-air computation (AirComp) for achieving sustainable wireless data aggregation (WDA) by integrating AirComp and wireless power transfer (WPT) into a joint design. In particular, we…
Multi-channel keyword spotting (KWS) has become crucial for voice-based applications in edge environments. However, its substantial computational and energy requirements pose significant challenges. We introduce ASAP-FE (Agile…
In wireless communication systems, the accurate and reliable evaluation of channel capacity is believed to be a fundamental and critical issue for terminals. However, with the rapid development of wireless technology, large-scale…
The all-to-all collective communications primitive is widely used in machine learning (ML) and high performance computing (HPC) workloads, and optimizing its performance is of interest to both ML and HPC communities. All-to-all is a…
We present a novel characterization of the mapping of multiple parallelism forms (e.g. data and model parallelism) onto hierarchical accelerator systems that is hierarchy-aware and greatly reduces the space of software-to-hardware mapping.…
Discrete optimization is a central problem in artificial intelligence. The optimization of the aggregated cost of a network of cost functions arises in a variety of problems including (W)CSP, DCOP, as well as optimization in stochastic…
Large language models (LLMs) have demonstrated remarkable success across various application domains, but their enormous sizes and computational demands pose significant challenges for deployment on resource-constrained edge devices. To…
This paper introduces a 71.2-$\mu$W speech recognition accelerator designed for edge devices' real-time applications, emphasizing an ultra low power design. Achieved through algorithm and hardware co-optimizations, we propose a compact…
6G wireless networks are expected to support diverse quality-of-service (QoS) demands while maintaining high energy efficiency. Weighted Minimum Mean Square Error (WMMSE) precoding with fixed user priorities and transmit power is widely…
Speech dereverberation is an important issue for many real-world speech processing applications. Among the techniques developed, the weighted prediction error (WPE) algorithm has been widely adopted and advanced over the last decade, which…
In this paper, we contend that the objective of representation learning is to compress and transform the distribution of the data, say sets of tokens, towards a mixture of low-dimensional Gaussian distributions supported on incoherent…
Fine-tuning of self-supervised models is a powerful transfer learning method in a variety of fields, including speech processing, since it can utilize generic feature representations obtained from large amounts of unlabeled data.…