Jun. Jui. 2020 Aug.
Click Seminar

Past Seminars

DateOctober 3, 2018 (Wednesday)
SpeakerHolakou Rahmanian 
ProfileDepartment of Computer Science,
University of California Santa Cruz
TitleOnline Dynamic Programming 
We consider the problem of repeatedly solving a variant of the same dynamic programming problem in successive trials. An instance of the type of problems we consider is to find a good binary search tree in a changing environment. At the beginning of each trial, the learner probabilistically chooses a tree with the n keys. The learner is then told the frequencies of the keys and is charged by the average search cost for the chosen tree. The problem is online because the frequencies can change between trials. The goal is to develop algorithms with the property that their total average search cost (loss) in all trials is close to the total loss of the best tree chosen in hindsight for all trials. The challenge, of course, is that the algorithm has to deal with exponential number of trees. We develop a general methodology for tackling such problems for arbitrary dynamic programming algorithms with min-sum recurrence relations. Our framework allows us to extend online learning algorithms like Expanded Hedge and Component Hedge to a significantly wider class of combinatorial objects than was possible before.
SiteBuilding 7 Room 235, Graduate School of Informatics, Kyoto University
Connected siteHokkaido-U VBL, Kanda Lab.