paper-with-me

홈 › Papers

Quantized Proximal Averaging Network for Analysis Sparse Coding

2021-05-13 · Kartheek Kumar Reddy Nareddy, Mani Madhoolika Bulusu, Praveen Kumar Pokala, Chandra Sekhar Seelamantula

We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the iterative algorithm into a trainable network that facilitates learning the sparsity prior. We also consider quantization of the network weights. Quantization makes neural networks efficient both in terms of memory and computation during inference, and also renders them compatible for low-precision hardware deployment. Our learning algorithm is based on a variant of the ADAM optimizer in which the quantizer is part of the forward pass and the gradients of the loss function are evaluated corresponding to the quantized weights while doing a book-keeping of the high-precision weights. We demonstrate applications to compressed image recovery and magnetic resonance image reconstruction. The proposed approach offers superior reconstruction accuracy and quality than state-of-the-art unfolding techniques and the performance degradation is minimal even when the weights are subjected to extreme quantization.

📄 PDF Abstract BibTeX arXiv:2105.06211

Code (0)

등록된 구현이 없습니다.

Tasks

Image ReconstructionQuantization

Methods 이 논문이 사용한 방법론

Adam 설명 없음

Similar Papers 제목 키워드 기반

Sparse Recovery and Dictionary Learning from Nonlinear Compressive Measurements

2019-09-10

Sparse coding and dictionary learning are popular techniques for linear inverse problems such as denoising or inpainting. However in many cases, the measurement process is nonlinear, for example for clipped, quantized or…

DenoisingDictionary Learning

A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication

2018-12-01 · NeurIPS 2018 12 · Peng Jiang, Gagan Agrawal

The large communication overhead has imposed a bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) for training deep neural networks. Previous works have demonstrated the potential of using gr…

Quantization

ProxQuant: Quantized Neural Networks via Proximal Operators

2018-10-01 · ICLR 2019 5 · Yu Bai, Yu-Xiang Wang, Edo Liberty

To make deep neural networks feasible in resource-constrained environments (such as mobile devices), it is beneficial to quantize models by using low-precision weights. One common technique for quantizing neural networks…

Quantization

Approximate search with quantized sparse representations

2016-08-10 · Himalaya Jain, Patrick Pérez, Rémi Gribonval, Joaquin Zepeda 외

This paper tackles the task of storing a large collection of vectors, such as visual descriptors, and of searching in it. To this end, we propose to approximate database vectors by constrained sparse coding, where possib…

Quantization

Learning Word Representations with Hierarchical Sparse Coding

2014-06-08 · Dani Yogatama, Manaal Faruqui, Chris Dyer, Noah A. Smith

We propose a new method for learning word representations using hierarchical regularization in sparse coding inspired by the linguistic study of word meanings. We show an efficient learning algorithm based on stochastic …

SentenceSentence CompletionSentiment AnalysisWord Similarity