Author

Ali Siahkoohi

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Jul 2026

Priors learned from legacy reconstructions inherit undetectable overconfidence

Where truths are scarce (e.g., seismic and medical imaging), learned priors in ill-posed inverse problems are trained on archives of legacy reconstructions---i.e., an older method's outputs---and their reported uncertainty is taken as data-driven. We show that this prior is, in the population limit, exactly the regular...

Ali Siahkoohi, Sina Alemohammad · 0 citations

#machine learning Preprint May 2026

A lift for input-convex neural net training

The lift is proposed, which replaces the free latent weight by a learnable slack plus an unconstrained network---the body---that takes a permutation-invariant summary of the training batch as input and couples to the gradient formed on it.

Ali Siahkoohi, Anirudh Thatipelli · 0 citations