Phase retrieval with application to optical imaging: a contemporary overview

Y Shechtman, YC Eldar, O Cohen… - IEEE signal …, 2015 - ieeexplore.ieee.org
The problem of phase retrieval, ie, the recovery of a function given the magnitude of its
Fourier transform, arises in various fields of science and engineering, including electron …

Discrimination-aware channel pruning for deep neural networks

Z Zhuang, M Tan, B Zhuang, J Liu… - Advances in neural …, 2018 - proceedings.neurips.cc
Channel pruning is one of the predominant approaches for deep model compression.
Existing pruning methods either train from scratch with sparsity constraints on channels, or …

Convolutional neural network based fault detection for rotating machinery

O Janssens, V Slavkovikj, B Vervisch… - Journal of Sound and …, 2016 - Elsevier
Vibration analysis is a well-established technique for condition monitoring of rotating
machines as the vibration patterns differ depending on the fault or machine condition …

On compressing deep models by low rank and sparse decomposition

X Yu, T Liu, X Wang, D Tao - Proceedings of the IEEE …, 2017 - openaccess.thecvf.com
Deep compression refers to removing the redundancy of parameters and feature maps for
deep learning models. Low-rank approximation and pruning for sparse structures play a vital …

[图书][B] Predictive analytics and data mining: concepts and practice with rapidminer

V Kotu, B Deshpande - 2014 - books.google.com
Put Predictive Analytics into ActionLearn the basics of Predictive Analysis and Data Mining
through an easy to understand conceptual framework and immediately practice the concepts …

Sparsity constrained nonlinear optimization: Optimality conditions and algorithms

A Beck, YC Eldar - SIAM Journal on Optimization, 2013 - SIAM
This paper treats the problem of minimizing a general continuously differentiable function
subject to sparsity constraints. We present and analyze several different optimality criteria …

Discrimination-aware network pruning for deep model compression

J Liu, B Zhuang, Z Zhuang, Y Guo… - … on Pattern Analysis …, 2021 - ieeexplore.ieee.org
We study network pruning which aims to remove redundant channels/kernels and hence
speed up the inference of deep networks. Existing pruning methods either train from scratch …

Hawkes processes for events in social media

MA Rizoiu, Y Lee, S Mishra, L Xie - Frontiers of multimedia research, 2017 - dl.acm.org
This chapter provides an accessible introduction for point processes, and especially Hawkes
processes, for modeling discrete, inter-dependent events over continuous time. We start by …

On iterative hard thresholding methods for high-dimensional m-estimation

P Jain, A Tewari, P Kar - Advances in neural information …, 2014 - proceedings.neurips.cc
The use of M-estimators in generalized linear regression models in high dimensional
settings requires risk minimization with hard L_0 constraints. Of the known methods, the …

Phase retrieval and design with automatic differentiation: tutorial

A Wong, B Pope, L Desdoigts, P Tuthill, B Norris… - JOSA B, 2021 - opg.optica.org
The principal limitation in many areas of astronomy, especially for directly imaging
exoplanets, arises from instability in the point spread function (PSF) delivered by the …