Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Nakakita, Shogo"'
This paper proposes a federated learning framework designed to achieve \textit{relative fairness} for clients. Traditional federated learning frameworks typically ensure absolute fairness by guaranteeing minimum performance across all client subgroup
Externí odkaz:
http://arxiv.org/abs/2411.01161
We consider a variant of the stochastic gradient descent (SGD) with a random learning rate and reveal its convergence properties. SGD is a widely used stochastic optimization algorithm in machine learning, especially deep learning. Numerous studies r
Externí odkaz:
http://arxiv.org/abs/2406.16032
Autor:
Nakakita, Shogo
We provide a novel dimension-free uniform concentration bound for the empirical risk function of constrained logistic regression. Our bound yields a milder sufficient condition for a uniform law of large numbers than conditions derived by the Rademac
Externí odkaz:
http://arxiv.org/abs/2405.18055
Autor:
Nakakita, Shogo
We study Langevin-type algorithms for sampling from Gibbs distributions such that the potentials are dissipative and their weak gradients have finite moduli of continuity not necessarily convergent to zero. Our main result is a non-asymptotic upper b
Externí odkaz:
http://arxiv.org/abs/2303.12407
We study the deviation inequality for a sum of high-dimensional random matrices and operators with dependence and arbitrary heavy tails. There is an increase in the importance of the problem of estimating high-dimensional matrices, and dependence and
Externí odkaz:
http://arxiv.org/abs/2210.09756
Autor:
Nakakita, Shogo
We propose an online parametric estimation method of stochastic differential equations with discrete observations and misspecified modelling based on online gradient descent. Our study provides uniform upper bounds for the risks of the estimators ove
Externí odkaz:
http://arxiv.org/abs/2210.08800
Autor:
Nakakita, Shogo, Imaizumi, Masaaki
The success of large-scale models in recent years has increased the importance of statistical models with numerous parameters. Several studies have analyzed over-parameterized linear models with high-dimensional data that may not be sparse; however,
Externí odkaz:
http://arxiv.org/abs/2204.08369
Autor:
Nakakita, Shogo H, Uchida, Masayuki
We propose a new statistical observation scheme of diffusion processes named convolutional observation, where it is possible to deal with smoother observation than ordinary diffusion processes by considering convolution of diffusion processes and som
Externí odkaz:
http://arxiv.org/abs/1906.10056
We consider parametric estimation for ergodic diffusion processes with noisy sampled data based on the hybrid method, that is, the multi-step estimation with the initial Bayes type estimators. In order to select proper initial values for optimisation
Externí odkaz:
http://arxiv.org/abs/1812.07497
Autor:
Nakakita, Shogo H., Uchida, Masayuki
We consider adaptive maximum-likelihood-type estimators and adaptive Bayes-type ones for discretely observed ergodic diffusion processes with observation noise whose variance is constant. The quasi-likelihood functions for the diffusion and drift par
Externí odkaz:
http://arxiv.org/abs/1806.09401