388 citations · 1.5k across the 94 of their papers we have counts for
20 papers · 1 filter
DP-MacAdam: Differentially Private Mechanism with Adaptive Clipping and Adaptive Momentum
Naima Tasnim, Lalitha Sankar, Oliver Kosut
Differentially private stochastic gradient descent (DP-SGD) has become the standard framework for privacy-preserving machine learning, yet its reliance on a fixed gradient clipping…
ArcMark: Distortion-Free Multi-Byte LLM Watermark via Optimal Transport
Atefeh Gilani, Sajani Vithana, Carol Xuan Long +3
Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into generated tokens that either flags LLM…
GeoClip: Geometry-Aware Clipping for Differentially Private SGD
Atefeh Gilani, Naima Tasnim, Lalitha Sankar +1
Differentially private stochastic gradient descent (DP-SGD) is the most widely used method for training machine learning models with provable privacy guarantees. A key challenge in…
Theoretical Guarantees of Data Augmented Last Layer Retraining Methods
Monica Welfert, Nathan Stromberg, Lalitha Sankar
Ensuring fair predictions across many distinct subpopulations in the training data can be prohibitive for large models. Recently, simple linear last layer retraining strategies, in…
Robustness to Subpopulation Shift with Domain Label Noise via Regularized Annotation of Domains
Nathan Stromberg, Rohan Ayyagari, Monica Welfert +3
Existing methods for last layer retraining that aim to optimize worst-group accuracy (WGA) rely heavily on well-annotated groups in the training data. We show, both in theory and p…
Parameter Optimization with Conscious Allocation (POCA)
Joshua Inman, Tanmay Khandait, Giulia Pedrielli +1
The performance of modern machine learning algorithms depends upon the selection of a set of hyperparameters. Common examples of hyperparameters are learning rate and the number of…