Center for Advanced Intelligence Project

Computational Learning Theory Team (https://www.riken.jp/en/research/labs/aip/generic_tech/comput_learn_theory/index.html) at RIKEN AIP

Speaker 1: Kohei Hatano (10 min.)
Title: Overview of Computational Learning TheoryTeam
Abstract: Computational Learning Theory Team investigates frontiers of intersections of learning theory (e.g., online learning), continuous/discrete optimization, and their applications. We briefly explain an overview of our team and some representative results.

Speaker 2: Sherief Hashima (35 min.)
Title: Bandit algorithms for 5G/6G wireless communication problems (working title)
Abstract: TBA

Speaker 3: Daiki Suehiro (35 min.)
Title: Theory and Algorithms for Shapelet-Based Multiple-Instance Learning (working title)
Abstract: TBA

Speaker 4: Yaxiong Liu (25 min.)
Title: Improved algorithms for online load balancing
Abstract: We consider an online load balancing problem and its extensions in the framework of repeated games. On each round, the player chooses a distribution (task allocation) over K servers, and then the environment reveals the load of each server, which determines the computation time of each server for processing the task assigned. After all rounds, the cost of the player is measured by some norm of the cumulative computation-time vector. The cost is the makespan if the norm is L_infty-norm. The goal is to minimize the regret, i.e., minimizing the player’s cost relative to the cost of the best fixed distribution in hindsight. We propose algorithms for general norms and prove their regret bounds. In particular, for L_infty-norm, our regret bound matches the best known bound and the proposed algorithm runs in polynomial time per trial involving linear programming and second order programming, whereas no polynomial time algorithm was previously known to achieve the bound.

Discussion and Conclusion (5 min)