6 citations · 11 across the 15 of their papers we have counts for
16 papers
On sample complexity for covariance estimation via the unadjusted Langevin algorithm
Shogo Nakakita
We establish sample complexity guarantees for estimating the covariance matrix of a strongly log-concave smooth distribution using the unadjusted Langevin algorithm (ULA). We quant…
Sparse estimation for the drift of high-dimensional Ornstein--Uhlenbeck processes with i.i.d. paths
Shogo Nakakita
We study sparsity-regularized maximum likelihood estimation for the drift parameter of high-dimensional non-stationary Ornstein--Uhlenbeck processes given repeated measurements of…
Improved generalization bounds for binary linear classification via isoperimetry
Shogo Nakakita
We examine the concentration of uniform generalization errors around their expectation in binary linear classification problems via an isoperimetric argument. In particular, we est…
Federated Learning with Relative Fairness
Shogo Nakakita, Tatsuya Kaneko, Shinya Takamaeda-Yamazaki +1
This paper proposes a federated learning framework designed to achieve \textit{relative fairness} for clients. Traditional federated learning frameworks typically ensure absolute f…
Effect of Random Learning Rate: Theoretical Analysis of SGD Dynamics in Non-Convex Optimization via Stationary Distribution
Naoki Yoshida, Shogo Nakakita, Masaaki Imaizumi
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 algor…
Dimension-free uniform concentration bound for logistic regression
Shogo Nakakita
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…
Non-asymptotic analysis of Langevin-type Monte Carlo algorithms
Shogo Nakakita
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 neces…
Parametric estimation of stochastic differential equations via online gradient descent
Shogo Nakakita
We propose an online parametric estimation method of stochastic differential equations with discrete observations and misspecified modelling based on online gradient descent. Our s…
Dimension-free Bounds for Sum of Dependent Matrices and Operators with Heavy-Tailed Distribution
Shogo Nakakita, Pierre Alquier, Masaaki Imaizumi
We prove deviation inequalities for sums of high-dimensional random matrices and operators with dependence and {\rc heavy tails}. Estimation of high-dimensional matrices is a conce…
Benign Overfitting in Time Series Linear Models with Over-Parameterization
Shogo Nakakita, Masaaki Imaizumi
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 line…
Parametric estimation for convolutionally observed diffusion processes
Shogo H Nakakita, Masayuki Uchida
We propose a new statistical observation scheme of diffusion processes named convolutional observation, where it is possible to deal with smoother observation than ordinary diffusi…
Hybrid estimation for ergodic diffusion processes based on noisy discrete observations
Yusuke Kaino, Shogo H. Nakakita, Masayuki Uchida
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…
Quasi-likelihood analysis of an ergodic diffusion plus noise
Shogo H. Nakakita, Masayuki Uchida
We consider adaptive maximum-likelihood-type estimators and adaptive Bayes-type ones for discretely observed ergodic diffusion processes with observation noise whose variance is co…
Inference for ergodic diffusions plus noise
Shogo H. Nakakita, Masayuki Uchida
We research adaptive maximum likelihood-type estimation for an ergodic diffusion process where the observation is contaminated by noise. This methodology leads to the asymptotic in…
Adaptive test for ergodic diffusions plus noise
Shogo H. Nakakita, Masayuki Uchida
We propose some parametric tests for ergodic diffusion-plus-noise model, which is a version of state-space modelling in statistics for stochastic diffusion equations. The test stat…
Adaptive estimation and noise detection for an ergodic diffusion with observation noises
Shogo H. Nakakita, Masayuki Uchida
We research adaptive maximum likelihood-type estimation for an ergodic diffusion process where the observation is contaminated by noise. This methodology leads to the asymptotic in…