Adversarial perturbation plays a significant role in the field of advers...
Differentially private (DP) optimization is the standard paradigm to lea...
We study the problem of differentially private (DP) fine-tuning of large...
Per-example gradient clipping is a key algorithmic step that enables
pra...
Large convolutional neural networks (CNN) can be difficult to train in t...
Interpretable machine learning has demonstrated impressive performance w...
Sparse Group LASSO (SGL) is a regularized model for high-dimensional lin...
In this paper, we consider the framework of privacy amplification via
it...
We show that adding differential privacy to Explainable Boosting Machine...
Sorted l1 regularization has been incorporated into many methods for sol...
In linear regression, SLOPE is a new convex analysis method that general...
Differentially Private-SGD (DP-SGD) of Abadi et al. (2016) and its varia...
When equipped with efficient optimization algorithms, the over-parameter...
A fundamental problem in the high-dimensional regression is to understan...
Deep learning models are often trained on datasets that contain sensitiv...
SLOPE is a relatively new convex optimization procedure for high-dimensi...