Variational Sparse Coding with Learned Thresholding. (arXiv:2205.03665v2 [cs.LG] UPDATED)

Sparse coding strategies have been lauded for their parsimonious
representations of data that leverage low dimensional structure. However,
inference of these codes typically relies on an optimization procedure with
poor computational scaling in high-dimensional problems. For example, sparse
inference in the representations learned in the high-dimensional intermediary
layers of deep neural networks (DNNs) requires an iterative minimization to be
performed at each training step. As such, recent, quick methods in variational
inference have been proposed to infer sparse codes by …

arxiv coding thresholding