Federated linear contextual bandits with user-level differential privacy
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 …
differential privacy (DP). We first introduce a unified federated bandits framework that can …
High dimensional differentially private stochastic optimization with heavy-tailed data
As one of the most fundamental problems in machine learning, statistics and differential
privacy, Differentially Private Stochastic Convex Optimization (DP-SCO) has been …
privacy, Differentially Private Stochastic Convex Optimization (DP-SCO) has been …
Collaborative ai teaming in unknown environments via active goal deduction
With the advancements of artificial intelligence (AI), we're seeing more scenarios that require
AI to work closely with other agents, whose goals and strategies might not be known …
AI to work closely with other agents, whose goals and strategies might not be known …
Stochastic graphical bandits with heavy-tailed rewards
We consider stochastic graphical bandits, where after pulling an arm, the decision maker
observes rewards of not only the chosen arm but also its neighbors in a feedback graph …
observes rewards of not only the chosen arm but also its neighbors in a feedback graph …
Distributed differential privacy in multi-armed bandits
SR Chowdhury, X Zhou - arXiv preprint arXiv:2206.05772, 2022 - arxiv.org
We consider the standard $ K $-armed bandit problem under a distributed trust model of
differential privacy (DP), which enables to guarantee privacy without a trustworthy server …
differential privacy (DP), which enables to guarantee privacy without a trustworthy server …
Byzantine-robust federated linear bandits
In this paper, we study a linear bandit optimization problem in a federated setting where a
large collection of distributed agents collaboratively learn a common linear bandit model …
large collection of distributed agents collaboratively learn a common linear bandit model …
Private stochastic optimization with large worst-case lipschitz parameter: Optimal rates for (non-smooth) convex losses and extension to non-convex losses
A Lowy, M Razaviyayn - International Conference on …, 2023 - proceedings.mlr.press
We study differentially private (DP) stochastic optimization (SO) with loss functions whose
worst-case Lipschitz parameter over all data points may be extremely large. To date, the vast …
worst-case Lipschitz parameter over all data points may be extremely large. To date, the vast …
On the statistical complexity of estimation and testing under privacy constraints
The challenge of producing accurate statistics while respecting the privacy of the individuals
in a sample is an important area of research. We study minimax lower bounds for classes of …
in a sample is an important area of research. We study minimax lower bounds for classes of …
On private and robust bandits
We study private and robust multi-armed bandits (MABs), where the agent receives Huber's
contaminated heavy-tailed rewards and meanwhile needs to ensure differential privacy. We …
contaminated heavy-tailed rewards and meanwhile needs to ensure differential privacy. We …
Decentralized randomly distributed multi-agent multi-armed bandit with heterogeneous rewards
We study a decentralized multi-agent multi-armed bandit problem in which multiple clients
are connected by time dependent random graphs provided by an environment. The reward …
are connected by time dependent random graphs provided by an environment. The reward …