We propose a reparametrization scheme to address the challenges of applying differentially
private SGD on large neural networks, which are 1) the huge memory cost of storing …

The prevalence of e-commerce has made customers' detailed personal information readily
accessible to retailers, and this information has been widely used in pricing decisions. When …

Consider the sequential optimization of a continuous, possibly non-convex, and expensive
to evaluate objective function $ f $. The problem can be cast as a Gaussian Process (GP) …

This paper studies federated linear contextual bandits under the notion of user-level
differential privacy (DP). We first introduce a unified federated bandits framework that can …

In this study, we delve into an emerging optimization challenge involving a black-box
objective function that can only be gauged via a ranking oracle-a situation frequently …

We study the problem of multi-armed bandits with ε-global Differential Privacy (DP). First, we
prove the minimax and problem-dependent regret lower bounds for stochastic and linear …

In recent decades, the advance of information technology and abundant personal data
facilitate the application of algorithmic personalized pricing. However, this leads to the …

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 …

Abstract We give an $(\varepsilon,\delta) $-differentially private algorithm for the Multi-Armed
Bandit (MAB) problem in the shuffle model with a distribution-dependent regret of $ O\left …

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 …