Drift estimation for a multi-dimensional diffusion process using deep neural networks

DOI10.1016/j.spa.2023.104240arXiv2112.13332MaRDI QIDQ6123258

Yuta Koike, Akihiro Oga

Publication date: 4 March 2024

Published in: Stochastic Processes and their Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.13332

zbMATH Keywords

minimax estimationleast squares estimationoracle inequalitydeep learningnonparametric drift estimation

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Nonparametric estimation (62G05) Artificial neural networks and deep learning (68T07) Markov processes: estimation; hidden Markov models (62M05)

Cites Work

• Unnamed Item
• Unnamed Item
• Sharp adaptive estimation of the drift function for ergodic diffusions
• Asymptotic statistical equivalence for ergodic diffusions: the multidimensional case
• Rates of convergence for empirical processes of stationary mixing sequences
• Statistical inference for ergodic diffusion processes.
• Comparison theorem and estimates for transition probability densities of diffusion processes
• Adaptive estimation in diffusion processes.
• Nonparametric estimation of scalar diffusions based on low frequency data
• Adaptive drift estimation for nonparametric diffusion model.
• Self-normalized processes: exponential inequalities, moment bounds and iterated logarithm laws.
• Weak convergence and empirical processes. With applications to statistics
• Approximate self-weighted LAD estimation of discretely observed ergodic Ornstein-Uhlenbeck processes
• Drift estimation on non compact support for diffusion models
• Estimation error analysis of deep learning on the regression problem on the variable exponent Besov space
• On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces
• Nonparametric statistical inference for drift vector fields of multi-dimensional diffusions
• Nonparametric regression using deep neural networks with ReLU activation function
• Optimization for deep learning: an overview
• Misspecified diffusion models with high-frequency observations and an application to neural networks
• Non parametric estimation of the diffusion coefficients of a diffusion with jumps
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Data driven time scale in Gaussian quasi-likelihood inference
• Sharp adaptive drift estimation for ergodic diffusions: the multivariate case
• Generalization bounds for non-stationary mixing processes
• Ergodic behavior of Markov processes. With applications to limit theorems
• Penalized nonparametric mean square estimation of the coefficients of diffusion processes
• Multidimensional diffusion processes.
• Exact adaptive pointwise drift estimation for multidimensional ergodic diffusions
• Yet Another Look at Harris’ Ergodic Theorem for Markov Chains
• Some Limit Theorems for Random Functions. I
• Inequalities for a Pair of Processes Stopped at a Random Time
• Mixing Conditions for Markov Chains
• ON THE FUNCTIONAL ESTIMATION OF MULTIVARIATE DIFFUSION PROCESSES
• High-Dimensional Probability
• Deep Neural Network Approximation Theory
• Nonconvex Sparse Regularization for Deep Neural Networks and Its Optimality
• Penalized nonparametric drift estimation for a multidimensional diffusion process
• Towards a Unified Approach for Proving Geometric Ergodicity and Mixing Properties of Nonlinear Autoregressive Processes
• Introduction to nonparametric estimation
• A deep network construction that adapts to intrinsic dimensionality beyond the domain

This page was built for publication: Drift estimation for a multi-dimensional diffusion process using deep neural networks