Lab Home | Phone | Search
	Center for Nonlinear Studies
	Home  ▶ People   Current   Executive Committee   Postdocs   Visitors   Students   Research   Publications  ▶ Conferences   Workshops   Sponsorship  ▶ Talks   Seminars   Postdoc Seminars Archive   Quantum Lunch   Quantum Lunch Archive   P/T Colloquia   Archive   Ulam Scholar     Postdoc Nominations  ▶ Student Requests   Student Program  ▶ Visitor Requests   Description   Past Visitors  ▶ Services   General     History of CNLS     Maps, Directions   CNLS Office   T-Division   LANL				Thursday, September 01, 20162:20 PM - 2:30 PMCNLS Conference Room (TA-3, Bldg 1690) Student Seminar Convolutional Dictionary Learning for Large-Scale, Distributed or Dynamic Datas Jialin LiuUniversity of California, Los Angeles Convolutional dictionary learning is a significant approach to train dictionaries for inverse problems in image processing. However, for large traing sets, state-of-the-art solvers are not efficient since their large time and memory costs. To fix this problem, we propose several algorithms for convolutional dictionary learning in the framework of distributed computing and online computing, which are efficient approaches for large-scale data sets. Simulation results of these methods are given and compared. Host: Chris Neale