Title: Online Learning Methods for Big Data Analytics
This tutorial was presented at IEEE ICDM2014, 17 December 2014.
Slides
Speakers
Dr Steven C.H. Hoi
School of Information Systems,
Singapore Management University
Institute for Infocomm Research (I2R), A*STAR, Singapore
Abstract
The advent of big data has been presenting a number of challenges and opportunities for research and development of scalable machine learning and data mining techniques. Conventional batch machine learning techniques suffer from many limitations when being applied to big data analytics tasks. In this tutorial, we will first introduce the motivation and background of big data analytics, and then focus on presenting the family of classical and latest online learning methods and algorithms, which are promising to tackle the emerging challenges of mining big data in a wide range of real-world applications. The main technical content of this tutorial consists of three parts: (i) online learning for linear classification, (ii) kernel-based online learning for nonlinear classification, and (iii) online learning for non-traditional learning tasks. We will also discuss some ongoing and future directions of large-scale machine learning (such as parallel and distributed online learning) for big data analytics applications.
Coverage
Introduction
• Big Data Analytics: Opportunities & Challenges
• Online Learning: What and Why
• Online Learning Applications
• Overview of Online Learning Methods
Online Learning Methods
• Traditional Linear Online Learning
• Non-traditional Linear Online Learning
• Kernel-based Online Learning
Discussions and Open Issues
Q&A
Bio of Speaker
Speaker:
Dr. Steven C. H. Hoi
Dr Steven C.H. Hoi is currently an Assistant Professor of the School of Computer Engineering at Nanyang Technological University, Singapore. He received his Bachelor degree in Computer Science from Tsinghua University, Beijing, P.R. China, in 2002, and both his Master and PhD degrees in Computer Science and Engineering from the Chinese University of Hong Kong, in 2004 and 2006, respectively. His research interests are machine learning and data mining and their applications to tackle challenges of real-world problems in several domains, including multimedia information retrieval (image and video search), social media, web search and data mining, computer vision and pattern recognition, bioinformatics, and computational finance. He has published over 100 referred papers in premier international journals and conferences in his research areas. He is fairly active in his research communities. In particular, he had served as General Co-chair for ACM SIGMM Workshops on Social Media (WSM'09, WSM'10, WSM'11), Program Co-Chair for the fourth Asian Conference on Machine Learning (ACML'12), Book editor for "Social Media Modeling and Computing", Guest editor for Machine Learning journal and ACM Transactions on Intelligent Systems and Technology, Area Chair/Senior Program Committee for conferences including ACM Multimedia 2012 and ACML'11, Technical PC member for many international conferences, and technical referee for top journals and magazines. He had been invited for external funds review by worldwide funding agencies, including the USA NSF funding agency, Hong Kong RGC funding agency, and some European funding agency. He is a member of ACM, AAAI, and IEEE.
Dr. Peilin Zhao
Dr. Peilin Zhao is currently a Research Scientist at Institute for Infocomm Research (I2R), A*STAR, Singapore. His research Interests are Online Learning, Stochastic Optimization and their applications. He was a visiting scholar at Baidu Research from Jan 2014 - Jun 2014, and a Postdoc Fellow with Prof Tong Zhang in the Department of Statistics, Rutgers University, from Sep 2013 - Jun 2014. He received his bachelor degree from Zhejiang university and his PHD degree (with thesis topic focused on the “Theory and Methods of Online Learning”) from the School of Computer Engineering, Nanyang Technological University, Singapore. In his research areas, he has published about 30 papers in top venues, including JMLR, ICML, NIPS, KDD, ICDM, etc.
