Zobrazeno 1 - 10
of 111
pro vyhledávání: '"Fukunaga, Takuro"'
Autor:
Ichikawa, Koji, Ito, Shinji, Hatano, Daisuke, Sumita, Hanna, Fukunaga, Takuro, Kakimura, Naonori, Kawarabayashi, Ken-ichi
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence 38 (2024) 12708-12716
We consider the sparse contextual bandit problem where arm feature affects reward through the inner product of sparse parameters. Recent studies have developed sparsity-agnostic algorithms based on the greedy arm selection policy. However, the analys
Externí odkaz:
http://arxiv.org/abs/2312.12400
Autor:
Sumita, Hanna, Ito, Shinji, Takemura, Kei, Hatano, Daisuke, Fukunaga, Takuro, Kakimura, Naonori, Kawarabayashi, Ken-ichi
We study online task assignment problem with reusable resources, motivated by practical applications such as ridesharing, crowdsourcing and job hiring. In the problem, we are given a set of offline vertices (agents), and, at each time, an online vert
Externí odkaz:
http://arxiv.org/abs/2203.07605
Autor:
Takemura, Kei, Ito, Shinji, Hatano, Daisuke, Sumita, Hanna, Fukunaga, Takuro, Kakimura, Naonori, Kawarabayashi, Ken-ichi
The contextual combinatorial semi-bandit problem with linear payoff functions is a decision-making problem in which a learner chooses a set of arms with the feature vectors in each round under given constraints so as to maximize the sum of rewards of
Externí odkaz:
http://arxiv.org/abs/2101.07957
Autor:
Fukunaga, Takuro
The problem of finding a minimum-weight connected dominating set (CDS) of a given undirected graph has been studied actively, motivated by operations of wireless ad hoc networks. In this paper, we formulate a new stochastic variant of the problem. In
Externí odkaz:
http://arxiv.org/abs/1912.12665
Autor:
Yabe, Akihiro, Hatano, Daisuke, Sumita, Hanna, Ito, Shinji, Kakimura, Naonori, Fukunaga, Takuro, Kawarabayashi, Ken-ichi
Bandit is a framework for designing sequential experiments. In each experiment, a learner selects an arm $A \in \mathcal{A}$ and obtains an observation corresponding to $A$. Theoretically, the tight regret lower-bound for the general bandit is polyno
Externí odkaz:
http://arxiv.org/abs/1806.02252
We consider the maximization problem of monotone submodular functions under an uncertain knapsack constraint. Specifically, the problem is discussed in the situation that the knapsack capacity is not given explicitly and can be accessed only through
Externí odkaz:
http://arxiv.org/abs/1803.02565
Autor:
Fukunaga, Takuro, Maehara, Takanori
We consider a new Steiner tree problem, called vertex-cover-weighted Steiner tree problem. This problem defines the weight of a Steiner tree as the minimum weight of vertex covers in the tree, and seeks a minimum-weight Steiner tree in a given vertex
Externí odkaz:
http://arxiv.org/abs/1701.08897
Autor:
Fukunaga, Takuro
Given an undirected graph on a node set $V$ and positive integers $k$ and $m$, a $k$-connected $m$-dominating set ($(k,m)$-CDS) is defined as a subset $S$ of $V$ such that each node in $V \setminus S$ has at least $m$ neighbors in $S$, and a $k$-conn
Externí odkaz:
http://arxiv.org/abs/1511.09156
Autor:
Fukunaga, Takuro
Kyoto University (京都大学)
0048
甲第12719号
情博第239号
新制||情||50(附属図書館)
UT51-2007-C255
学位規則第4条第1項該当
0048
甲第12719号
情博第239号
新制||情||50(附属図書館)
UT51-2007-C255
学位規則第4条第1項該当
Externí odkaz:
http://hdl.handle.net/2433/93464
Autor:
Fukunaga, Takuro
We consider a network design problem called the generalized terminal backup problem. Whereas earlier work investigated the edge-connectivity constraints only, we consider both edge- and node-connectivity constraints for this problem. A major contribu
Externí odkaz:
http://arxiv.org/abs/1409.5561