Online Learning With Incremental Feature Space and Bandit Feedback

Author:

Gu Shilin1ORCID,Luo Tingjin1ORCID,He Ming2ORCID,Hou Chenping1ORCID

Affiliation:

1. College of Science, National University of Defense Technology, Changsha, Hunan, China

2. Command and Control Engineering College, People's Liberation Army Engineering University, Nanjing, Jiangsu, China

Funder

National Key Research and Development Program of China

Key NSF of China

National Natural Science Foundation of China

NSF for Huxiang Young Talents Program of Hunan Province

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Computer Science Applications,Information Systems

Reference40 articles.

1. Efficient online bandit multiclass learning with $\tilde{O}(\sqrt{T})$O˜(T) regret;beygelzimer;Proc 34th Int Conf Mach Learn,2017

2. Passive-aggressive bounds in bandit feedback classification;zhong;Proc Eur Conf Mach Learn Princ Pract Knowl Discov Databases,2015

3. Newtron: An efficient bandit algorithm for online multiclass prediction;hazan;Proc Adv Neural Inf Process Syst,2011

4. Online passive-aggressive algorithms;crammer;J Mach Learn Res,2006

5. Boosting with online binary learners for the multiclass bandit problem;chen;Proc Int Conf Mach Learn,2014

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3