Zobrazeno 1 - 10
of 112
pro vyhledávání: '"Nakano, Yumiharu"'
Autor:
Nakano, Yumiharu
We theoretically analyze the original version of the denoising diffusion probabilistic models (DDPMs) presented in Ho, J., Jain, A., and Abbeel, P., Advances in Neural Information Processing Systems, 33 (2020), pp. 6840-6851. Our main theorem states
Externí odkaz:
http://arxiv.org/abs/2406.01320
Autor:
Endo, Koya, Nakano, Yumiharu
We consider the weak convergence of the Euler-Maruyama approximation for Schr\"odinger-F\"ollmer diffusions, which are solutions of Schr\"odinger bridge problems and can be used for sampling from given distributions. We show that the distribution of
Externí odkaz:
http://arxiv.org/abs/2403.03446
Autor:
Nakano, Yumiharu
We characterize the Schr\"odinger bridge problems by a family of Mckean-Vlasov stochastic control problems with no terminal time distribution constraint. In doing so, we use the theory of Hilbert space embeddings of probability measures and then desc
Externí odkaz:
http://arxiv.org/abs/2310.14522
Autor:
Nakano, Yumiharu
We study an inverse problem of the stochastic optimal control of general diffusions with performance index having the quadratic penalty term of the control process. Under mild conditions on the system dynamics, the cost functions, and the optimal con
Externí odkaz:
http://arxiv.org/abs/2005.11485
Autor:
Kinoshita, Yuki, Nakano, Yumiharu
We propose kernel-based collocation methods for numerical solutions to Heath-Jarrow-Morton models with Musiela parametrization. The methods can be seen as the Euler-Maruyama approximation of some finite dimensional stochastic differential equations,
Externí odkaz:
http://arxiv.org/abs/1809.05643
Autor:
Nakano, Yumiharu
We prove that the functions constructed by the kernel-based regressions with Wendland kernels under $\ell_1$-norm constraints converge to unique viscosity solutions of the corresponding fully nonlinear parabolic equations. A key ingredient in our pro
Externí odkaz:
http://arxiv.org/abs/1803.09446
Autor:
Nakano, Yumiharu
We examine an application of the kernel-based interpolation to numerical solutions for Zakai equations in nonlinear filtering, and aim to prove its rigorous convergence. To this end, we find the class of kernels and the structure of collocation point
Externí odkaz:
http://arxiv.org/abs/1710.09090
Autor:
Nakano, Yumiharu
This note presents a kind of the strong law of large numbers for an insurance risk caused by a single catastrophic event rather than by an accumulation of independent and identically distributed risks. We derive this result by a large diversification
Externí odkaz:
http://arxiv.org/abs/1601.03171
Autor:
Nakano, Yumiharu
We propose numerical integration methods for Choquet integrals where the capacities are given by distortion functions of an underlying probability measure. It relies on the explicit representation of the integrals for step functions and can be seen a
Externí odkaz:
http://arxiv.org/abs/1411.0773
Autor:
Nakano, Yumiharu
We prove the convergence of meshfree collocation methods for the terminal value problems of fully nonlinear parabolic partial differential equations in the framework of viscosity solutions, provided that the basis function approximations of the termi
Externí odkaz:
http://arxiv.org/abs/1408.5195