The remarkable performance of deep Convolutional neural networks (CNNs) is generally
attributed to their deeper and wider architectures, which can come with significant …

Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

In response to recent data regulation requirements, machine unlearning (MU) has emerged
as a critical process to remove the influence of specific examples from a given model …

In the past decade, advances in deep learning have resulted in breakthroughs in a variety of
areas, including computer vision, natural language understanding, speech recognition, and …

Pruning the parameters of deep neural networks has generated intense interest due to
potential savings in time, memory and energy both during training and at test time. Recent …

The advancements in machine learning (ML) opened a new opportunity to bring intelligence
to the low-end Internet-of-Things (IoT) nodes, such as microcontrollers. Conventional ML …

Vision transformers (ViTs) have recently received explosive popularity, but their enormous
model sizes and training costs remain daunting. Conventional post-training pruning often …

In natural language processing (NLP), enormous pre-trained models like BERT have
become the standard starting point for training on a range of downstream tasks, and similar …

We study whether a neural network optimizes to the same, linearly connected minimum
under different samples of SGD noise (eg, random data order and augmentation). We find …

Federated learning (FL) allows model training from local data collected by edge/mobile
devices while preserving data privacy, which has wide applicability to image and vision …