2 papers
cs.LG2025
Variational Deep Learning via Implicit Regularization
Jonathan Wenger, Beau Coker, Juraj Marusic +1
Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theor…
stat.ML2025
Differentially Private Hyperparameter Tuning using Local Bayesian Optimization
Getoar Sopa, Juraj Marusic, Marco Avella Medina +1
Hyperparameter tuning is a key component of machine learning procedures, but when validation data contain sensitive user information, search mechanisms can leak private information…