← Search

Naoki Kiyohara

2 accepted papers

2025

Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions

NeurIPS 2025poster

Stochastic differential equations (SDEs) are well suited to modelling noisy and/or irregularly-sampled time series, which are omnipresent in finance, physics, and machine learning applications. Traditional approaches require costly simulation of numerical solvers when sampling between arbitrary time…

Cited by 0SourceScholar
2025

Recurrent Memory for Online Interdomain Gaussian Processes

NeurIPS 2025poster

We propose a novel online Gaussian process (GP) model that is capable of capturing long-term memory in sequential data in an online learning setting. Our model, Online HiPPO Sparse Variational Gaussian Process (OHSVGP), leverages the HiPPO (High-order Polynomial Projection Operators) framework, whic…

Cited by 0SourceScholar