Successful integration of deep neural networks (DNNs) or deep learning (DL) has resulted
in breakthroughs in many areas. However, deploying these highly accurate models for data …

The rapid uptake of mobile devices and the rising popularity of mobile applications and
services pose unprecedented demands on mobile and wireless networking infrastructure …

The well-known ancient Chinese philosopher Lao Tzu (老子) or Laozi (6th∼ 4th century BC
during the Spring and Autumn period) started his classic Tao Teh Ching《 道德经》 or Dao De …

On-device training enables the model to adapt to new data collected from the sensors by
fine-tuning a pre-trained model. Users can benefit from customized AI models without having …

Reinforcement learning has achieved great success in many applications. However, sample
efficiency remains a key challenge, with prominent methods requiring millions (or even …

We introduce ProxSkip—a surprisingly simple and provably efficient method for minimizing
the sum of a smooth ($ f $) and an expensive nonsmooth proximable ($\psi $) function. The …

Large Language Models (LLMs) have demonstrated remarkable capabilities in important
tasks such as natural language understanding and language generation, and thus have the …

Generative large language model (LLM) applications are growing rapidly, leading to large-
scale deployments of expensive and power-hungry GPUs. Our characterization of LLM …

The purpose of this study is to introduce new design-criteria for next-generation
hyperparameter optimization software. The criteria we propose include (1) define-by-run API …

Most cross-device federated learning (FL) studies focus on the model-homogeneous setting
where the global server model and local client models are identical. However, such …