Weijie Su

On Learning Rates and Schrödinger Operators

2020 · arXiv (Cornell University)

The learning rate is perhaps the single most important parameter in the training of neural networks and, more broadly, in stochastic (nonconvex) optimization. Accordingly, there are numerous effective, but poorly understood, techniques for tuning the …

Federated <i>f</i>-Differential Privacy.

2021 · PubMed

-differential privacy. Finally, we empirically demonstrate the trade-off between privacy guarantee and prediction performance for models trained by PriFedSync in computer vision tasks.

DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework

2023 · arXiv (Cornell University)

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 …