collaborators

5 papers

cs.LG2026

Correcting Class Imbalance in Prior-Data Fitted Networks for Tabular Classification

Samuel McDowell, Nathan Stromberg, Lalitha Sankar

Prior-data fitted networks (PFNs) have achieved exceptional performance on tabular classification tasks. However, like other classifiers, their performance can suffer under the eff…

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…

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

POCAII: Parameter Optimization with Conscious Allocation using Iterative Intelligence

Joshua Inman, Tanmay Khandait, Lalitha Sankar +1

In this paper we propose for the first time the hyperparameter optimization (HPO) algorithm POCAII. POCAII differs from the Hyperband and Successive Halving literature by explicitl…

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…