Overparameterized networks trained to convergence have shown impressive performance
in domains such as computer vision and natural language processing. Pushing state of the …

This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …

We design a family of image classification architectures that optimize the trade-off between
accuracy and efficiency in a high-speed regime. Our work exploits recent findings in …

While neural networks have advanced the frontiers in many applications, they often come at
a high computational cost. Reducing the power and latency of neural network inference is …

Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved
great success and become a milestone in the field of artificial intelligence (AI). Owing to …

Distributed training of foundation models, especially large language models (LLMs), is
communication-intensive and so has heavily relied on centralized data centers with fast …

Recent advancements in machine learning achieved by Deep Neural Networks (DNNs)
have been significant. While demonstrating high accuracy, DNNs are associated with a …

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-
point value is the predominant approach. We find that, perhaps surprisingly, this is not the …

Despite the soaring use of convolutional neural networks (CNNs) in mobile applications,
uniformly sustaining high-performance inference on mobile has been elusive due to the …

Transformer-based pre-training models like BERT have achieved remarkable performance
in many natural language processing tasks. However, these models are both computation …