Zobrazeno 1 - 10
of 17 169
pro vyhledávání: '"A. Kashima"'
Autor:
Mori, Junki, Kihara, Kosuke, Miyagawa, Taiki, Ebihara, Akinori F., Teranishi, Isamu, Kashima, Hisashi
Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this problem, we focus on a source-free domain adaptation task, where (1)
Externí odkaz:
http://arxiv.org/abs/2412.13757
Autor:
Suehara, Tsuyoshi, Takeuchi, Koh, Kashima, Hisashi, Oyama, Satoshi, Sakurai, Yuko, Yokoo, Makoto
Mechanism design, a branch of economics, aims to design rules that can autonomously achieve desired outcomes in resource allocation and public decision making. The research on mechanism design using machine learning is called automated mechanism desi
Externí odkaz:
http://arxiv.org/abs/2412.11465
Large Language Models (LLMs) are trained on large corpora written by humans and demonstrate high performance on various tasks. However, as humans are susceptible to cognitive biases, which can result in irrational judgments, LLMs can also be influenc
Externí odkaz:
http://arxiv.org/abs/2412.00323
Autor:
Ito, Kaito, Kashima, Kenji
This paper introduces the risk-sensitive control as inference (RCaI) that extends CaI by using R\'{e}nyi divergence variational inference. RCaI is shown to be equivalent to log-probability regularized risk-sensitive control, which is an extension of
Externí odkaz:
http://arxiv.org/abs/2411.01827
Autor:
Rigaux, Tomas, Kashima, Hisashi
Mastering games is a hard task, as games can be extremely complex, and still fundamentally different in structure from one another. While the AlphaZero algorithm has demonstrated an impressive ability to learn the rules and strategy of a large variet
Externí odkaz:
http://arxiv.org/abs/2410.23753
Designing effective two-sided matching mechanisms is a major problem in mechanism design, and the goodness of matching cannot always be formulated. The existing work addresses this issue by searching over a parameterized family of mechanisms with cer
Externí odkaz:
http://arxiv.org/abs/2410.19384
The fair allocation of indivisible resources is a fundamental problem. Existing research has developed various allocation mechanisms or algorithms to satisfy different fairness notions. For example, round robin (RR) was proposed to meet the fairness
Externí odkaz:
http://arxiv.org/abs/2410.17500
Question answering (QA) tasks have been extensively studied in the field of natural language processing (NLP). Answers to open-ended questions are highly diverse and difficult to quantify, and cannot be simply evaluated as correct or incorrect, unlik
Externí odkaz:
http://arxiv.org/abs/2410.01246
Intransitivity is a critical issue in pairwise preference modeling. It refers to the intransitive pairwise preferences between a group of players or objects that potentially form a cyclic preference chain and has been long discussed in social choice
Externí odkaz:
http://arxiv.org/abs/2409.19325
Autor:
Kashima, Masaki, Zhu, Xuding
A proper $k$-coloring of $G$ is called an odd coloring of $G$ if for every vertex $v$, there is a color that appears at an odd number of neighbors of $v$. This concept was introduced recently by Petru\v{s}evski and \v{S}krekovski, and they conjecture
Externí odkaz:
http://arxiv.org/abs/2407.19362