6 papers · 1 filter
Stable and Privacy-Preserving Synthetic Educational Data with Empirical Marginals: A Copula-Based Approach
Gabriel Diaz Ramos, Lorenzo Luzi, Debshila Basu Mallick +1
To advance Educational Data Mining (EDM) within strict privacy-protecting regulatory frameworks, researchers must develop methods that enable data-driven analysis while protecting…
Improving Fairness and Mitigating MADness in Generative Models
Paul Mayer, Lorenzo Luzi, Ali Siahkoohi +2
Generative models unfairly penalize data belonging to minority classes, suffer from model autophagy disorder (MADness), and learn biased estimates of the underlying distribution pa…
Self-Consuming Generative Models Go MAD
Sina Alemohammad, Josue Casco-Rodriguez, Lorenzo Luzi +5
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models. Repeating this…
NFT-K: Non-Fungible Tangent Kernels
Sina Alemohammad, Hossein Babaei, CJ Barberan +4
Deep neural networks have become essential for numerous applications due to their strong empirical performance such as vision, RL, and classification. Unfortunately, these networks…
Ensembles of Generative Adversarial Networks for Disconnected Data
Lorenzo Luzi, Randall Balestriero, Richard G. Baraniuk
Most current computer vision datasets are composed of disconnected sets, such as images from different classes. We prove that distributions of this type of data cannot be represent…
Subspace Fitting Meets Regression: The Effects of Supervision and Orthonormality Constraints on Double Descent of Generalization Errors
Yehuda Dar, Paul Mayer, Lorenzo Luzi +1
We study the linear subspace fitting problem in the overparameterized setting, where the estimated subspace can perfectly interpolate the training examples. Our scope includes the…