5 papers · 1 filter
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…
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.…
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…
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…
Label Noise Robustness for Domain-Agnostic Fair Corrections via Nearest Neighbors Label Spreading
Nathan Stromberg, Rohan Ayyagari, Sanmi Koyejo +2
Last-layer retraining methods have emerged as an efficient framework for correcting existing base models. Within this framework, several methods have been proposed to deal with cor…