4 papers
Priors learned from legacy reconstructions inherit undetectable overconfidence
Ali Siahkoohi, Sina Alemohammad
Where truths are scarce (e.g., seismic and medical imaging), a prior for an ill-posed inverse problem is trained on an archive of legacy reconstructions---an older method's outputs…
A lift for input-convex neural network training
Ali Siahkoohi, Anirudh Thatipelli
Input-convex neural networks (ICNNs) are widely used for log-concave density estimation, convex-potential normalizing flows, optimal transport, and transport-map inversion for high…
Hypernetwork-based approach for grid-independent functional data clustering
Anirudh Thatipelli, Ali Siahkoohi
Functional data clustering is concerned with grouping functions that share similar structure, yet most existing methods implicitly operate on sampled grids, causing cluster assignm…
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…