With the rapid development of low-cost consumer electronics and pervasive adoption of next
generation wireless communication technologies, a tremendous amount of data has been …

Collecting and analyzing massive data generated from smart devices have become
increasingly pervasive in crowdsensing, which are the building blocks for data-driven …

A trustworthy reinforcement learning algorithm should be competent in solving challenging
real-world problems, including {robustly} handling uncertainties, satisfying {safety} …

Most of our lives are conducted in the cyberspace. The human notion of privacy translates
into a cyber notion of privacy on many functions that take place in the cyberspace. This …

The cloud-edge-terminal collaborative network (CETCN) is considered as a novel paradigm
for emerging applications owing to its huge potential in providing low-latency and ultra …

Reinforcement learning algorithms are widely used in domains where it is desirable to
provide a personalized service. In these domains it is common that user data contains …

Exploiting the computing capability of mobile devices with specialized engines (eg, Neural
Engine in iPhone), an attractive paradigm of federated learning that combines the mobile …

Motivated by the wide adoption of reinforcement learning (RL) in real-world personalized
services, where users' sensitive and private information needs to be protected, we study …

The offline reinforcement learning (RL) problem is often motivated by the need to learn data-
driven decision policies in financial, legal and healthcare applications. However, the learned …

We investigate the problem of private read-update-write (PRUW) in relation to private
federated submodel learning (FSL), where a machine learning model is divided into multiple …