Zobrazeno 1 - 10
of 167
pro vyhledávání: '"Kanazawa, Takuya"'
Autor:
Kanazawa, Takuya, Gupta, Chetan
Publikováno v:
Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning -- ICANN 2023. Lecture Notes in Computer Science, vol 14259, pp 63--76. Springer, Cham
Sequential decision making in the real world often requires finding a good balance of conflicting objectives. In general, there exist a plethora of Pareto-optimal policies that embody different patterns of compromises between objectives, and it is te
Externí odkaz:
http://arxiv.org/abs/2303.08909
Autor:
Kanazawa, Takuya, Gupta, Chetan
Publikováno v:
Proceedings of the 14th International Joint Conference on Computational Intelligence - Volume 1: NCTA, 292-304, 2022 , Valletta, Malta
Development of an accurate, flexible, and numerically efficient uncertainty quantification (UQ) method is one of fundamental challenges in machine learning. Previously, a UQ method called DISCO Nets has been proposed (Bouchacourt et al., 2016), which
Externí odkaz:
http://arxiv.org/abs/2209.08418
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 2022, pp. 1-10
Uncertainty quantification is one of the central challenges for machine learning in real-world applications. In reinforcement learning, an agent confronts two kinds of uncertainty, called epistemic uncertainty and aleatoric uncertainty. Disentangling
Externí odkaz:
http://arxiv.org/abs/2207.13730
Autor:
Kanazawa, Takuya, Wettig, Tilo
We consider non-Hermitian Dirac operators in QCD-like theories coupled to a chiral U(1) potential or an imaginary chiral chemical potential. We show that in the continuum they fall into the recently discovered universality classes AI$^\dagger$ or AII
Externí odkaz:
http://arxiv.org/abs/2111.04573
Autor:
Kanazawa, Takuya
Publikováno v:
2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 2022, pp. 1-8
Bayesian optimization (BO) with Gaussian processes is a powerful methodology to optimize an expensive black-box function with as few function evaluations as possible. The expected improvement (EI) and probability of improvement (PI) are among the mos
Externí odkaz:
http://arxiv.org/abs/2104.12363
Autor:
Kanazawa, Takuya, Wettig, Tilo
Publikováno v:
Phys. Rev. D 104, 014509 (2021)
In non-Hermitian random matrix theory there are three universality classes for local spectral correlations: the Ginibre class and the nonstandard classes $\mathrm{AI}^\dagger$ and $\mathrm{AII}^\dagger$. We show that the continuum Dirac operator in t
Externí odkaz:
http://arxiv.org/abs/2104.05846
Autor:
Kanazawa, Takuya
Bayesian optimization is a powerful tool to optimize a black-box function, the evaluation of which is time-consuming or costly. In this paper, we propose a new approach to Bayesian optimization called GP-MGC, which maximizes multiscale graph correlat
Externí odkaz:
http://arxiv.org/abs/2103.09434
Autor:
Kanazawa, Takuya
We propose a novel approach for Bayesian optimization, called $\textsf{GP-DC}$, which combines Gaussian processes with distance correlation. It balances exploration and exploitation automatically, and requires no manual parameter tuning. We evaluate
Externí odkaz:
http://arxiv.org/abs/2102.08993
Publikováno v:
J. High Energ. Phys. 2021, 15 (2021)
We investigate a model of interacting Dirac fermions in $2+1$ dimensions with $M$ flavors and $N$ colors having the $\mathrm{U}(M)\times \mathrm{SU}(N)$ symmetry. In the large-$N$ limit, we find that the $\mathrm{U}(M)$ symmetry is spontaneously brok
Externí odkaz:
http://arxiv.org/abs/2102.09089