← Search

Milan Shen

2 accepted papers

2023

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization

NeurIPS 2023poster

Hyperparameter optimization, also known as hyperparameter tuning, is a widely recognized technique for improving model performance. Regrettably, when training private ML models, many practitioners often overlook the privacy risks associated with hyperparameter optimization, which could potentially e…

Cited by 8SourcePDFScholar
2023

Federated Linear Contextual Bandits with User-level Differential Privacy

ICML 2023poster

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 accommodate various definitions of DP in the sequential decision-making setting. We then formally introduce user-level ce…

Cited by 18SourcePDFScholar