_{약력: Changhee Joo received his Ph.D. degree from Seoul National University, Korea. Since 2005, he was with Purdue University and the Ohio State University, and joined Korea University of Technology and Education, Korea, in 2010. He is now with UNIST, Korea. His research interests include resource allocation in wireless networks, network optimization, wireless sensor networks, and Internet protocols. He is an associated editor of IEEE/ACM Transactions on Networking, an editor of the Journal of Communications and Networks, and has served several primary conferences as a technical committee member, includingthe IEEE International Conference on Communications (INFOCOM), the IEEE Communications Society Conference on Sensing, Communication, and Networking (SECON), and the ACM Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc). Dr. Joo is a recipient of the IEEE INFOCOM 2008 best paper award, the ICTC 2015 best paper award, and the KICS Haedong Young Scholar Award (2014).}

_{초록: In Cognitive Radio Networks (CRNs), dynamic spectrum access allows (unlicensed) users to identify and access unused channels opportunistically, thus improves spectrum utility. In this paper, we address the user-channel allocation problem in multi-user multi-channel CRNs without a prior knowledge of channel statistics. A reward of a channel is stochastic with unknown distribution, and statistically different for each user. Each user either explores a channel to learn the channel statistics, or exploits the channel with the highest expected reward based on information collected so far. Further, a channel should be accessed exclusively by one user at a time due to a collision. Using multi-armed bandit framework, we develop a provably efficient solution whose computational complexity is linear to the number of users and channels.}