paper-with-me

Papers

Learning step sizes for unfolded sparse coding

2019-05-27 · NeurIPS 2019 12 · Pierre Ablin, Thomas Moreau, Mathurin Massias, Alexandre Gramfort

Sparse coding is typically solved by iterative optimization techniques, such as the Iterative Shrinkage-Thresholding Algorithm (ISTA). Unfolding and learning weights of ISTA using neural networks is a practical way to accelerate estimation. In this paper, we study the selection of adapted step sizes for ISTA. We show that a simple step size strategy can improve the convergence rate of ISTA by leveraging the sparsity of the iterates. However, it is impractical in most large-scale applications. Therefore, we propose a network architecture where only the step sizes of ISTA are learned. We demonstrate that for a large class of unfolded algorithms, if the algorithm converges to the solution of the Lasso, its last layers correspond to ISTA with learned step sizes. Experiments show that our method is competitive with state-of-the-art networks when the solutions are sparse enough.

📄 PDF Abstract BibTeX arXiv:1905.11071

Code (1)

tomMoral/adopty 공식 구현

Similar Papers 제목 키워드 기반

Learning unfolded networks with a cyclic group structure

2022-11-16 · Emmanouil Theodosis, Demba Ba

Deep neural networks lack straightforward ways to incorporate domain knowledge and are notoriously considered black boxes. Prior works attempted to inject domain knowledge into architectures implicitly through data augme…

Data AugmentationRotated MNIST

Alternative design of DeepPDNet in the context of image restoration

2022-02-20 · Mingyuan Jiu, Nelly Pustelnik

This work designs an image restoration deep network relying on unfolded Chambolle-Pock primal-dual iterations. Each layer of our network is built from Chambolle-Pock iterations when specified for minimizing a sum of a $\…

Image Restoration

Convolutional Dictionary Learning in Hierarchical Networks

2019-07-23 · Javier Zazo, Bahareh Tolooshams, Demba Ba

Filter banks are a popular tool for the analysis of piecewise smooth signals such as natural images. Motivated by the empirically observed properties of scale and detail coefficients of images in the wavelet domain, we p…

Dictionary Learning

Learned Greedy Method (LGM): A Novel Neural Architecture for Sparse Coding and Beyond

2020-10-14 · Rajaei Khatib, Dror Simon, Michael Elad

The fields of signal and image processing have been deeply influenced by the introduction of deep neural networks. These are successfully deployed in a wide range of real-world applications, obtaining state of the art re…

Lightweight Adaptive ReduNet via Hyperspherical Manifold Learning

2026-08-21 · Zhenglin Huang, Qifa Yan, Bin Dai, Xiaohu Tang arxiv

In recent years, a white-box neural network called ReduNet has been proposed, which employs the maximal coding rate reduction (MCR$^2$) principle to transform raw data into low-dimensional discriminative features via a f…