Deep learning methods for solving linear inverse problems: Research directions and paradigms

Y Bai, W Chen, J Chen, W Guo - Signal Processing, 2020 - Elsevier
The linear inverse problem is fundamental to the development of various scientific areas.
Innumerable attempts have been carried out to solve different variants of the linear inverse …

Identifiable deep generative models via sparse decoding

GE Moran, D Sridhar, Y Wang, DM Blei - ar** the activity of early visual cortex
F Csikor, B Meszéna, G Orbán - BioRxiv, 2023 - biorxiv.org
Deep discriminative models provide remarkable insights into hierarchical processing in the
brain by predicting neural activity along the visual pathway. However, these models differ …

On incorporating inductive biases into vaes

N Miao, E Mathieu, N Siddharth, YW Teh… - arxiv preprint arxiv …, 2021 - arxiv.org
We explain why directly changing the prior can be a surprisingly ineffective mechanism for
incorporating inductive biases into VAEs, and introduce a simple and effective alternative …