5 papers
Which Similarity-Sensitive Entropy (Sentropy)?
Phuc Nguyen, Josiah Couch, Rahul Bansal +5
Shannon entropy is not the only entropy that is relevant to machine-learning datasets, nor possibly even the most important one. Traditional entropies such as Shannon entropy captu…
Generative deep learning for foundational video translation in ultrasound
Nikolina Tomic, Roshni Bhatnagar, Sarthak Jain +4
Deep learning (DL) has the potential to revolutionize image acquisition and interpretation across medicine, however, attention to data imbalance and missingness is required. Ultras…
GEM-T: Generative Tabular Data via Fitting Moments
Miao Li, Phuc Nguyen, Christopher Tam +6
Tabular data dominates data science but poses challenges for generative models, especially when the data is limited or sensitive. We present a novel approach to generating syntheti…
X-Factor: Quality Is a Dataset-Intrinsic Property
Josiah Couch, Miao Li, Rima Arnaout +1
In the universal quest to optimize machine-learning classifiers, three factors -- model architecture, dataset size, and class balance -- have been shown to influence test-time perf…
Grade Inflation in Generative Models
Phuc Nguyen, Miao Li, Alexandra Morgan +2
Generative models hold great potential, but only if one can trust the evaluation of the data they generate. We show that many commonly used quality scores for comparing two-dimensi…