3 papers
cs.LG2025
Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining
Nathan Stromberg, Christos Thrampoulidis, Lalitha Sankar
While machine learning models become more capable in discriminative tasks at scale, their ability to overcome biases introduced by training data has come under increasing scrutiny.…
cs.LG2025
CORAL: Disentangling Latent Representations in Long-Tailed Diffusion
Esther Rodriguez, Monica Welfert, Samuel McDowell +3
Diffusion models have achieved impressive performance in generating high-quality and diverse synthetic data. However, their success typically assumes a class-balanced training dist…
stat.ML2025
Lower Bounds on the MMSE of Adversarially Inferring Sensitive Features
Monica Welfert, Nathan Stromberg, Mario Diaz +1
We propose an adversarial evaluation framework for sensitive feature inference based on minimum mean-squared error (MMSE) estimation with a finite sample size and linear predictive…