Markus Heinonen

LEARNING STOCHASTIC DIFFERENTIAL EQUATIONS WITH GAUSSIAN PROCESSES WITHOUT GRADIENT MATCHING

2018

We introduce a novel paradigm for learning non-parametric drift and diffusion functions for stochastic differential equation (SDE). The proposed model learns to simulate path distributions that match observations with non-uniform time increments and arbitrary sparseness, …

Deep learning with differential Gaussian process flows

2018 · Research Explorer (The University of Manchester)

We propose a novel deep learning paradigm of differential flows that learn a stochastic differential equation transformations of inputs prior to a standard classification or regression function. The key property of differential Gaussian processes is …

Variational multiple shooting for Bayesian ODEs with Gaussian processes

2021 · arXiv (Cornell University)

Recent machine learning advances have proposed black-box estimation of unknown continuous-time system dynamics directly from data. However, earlier works are based on approximative ODE solutions or point estimates. We propose a novel Bayesian nonparametric model …

Multi-target property prediction and optimization using latent spaces of generative model

2025 · Machine Learning Science and Technology

Abstract Multi-target property prediction has the potential to improve generalization by exploiting the positive transfer between targets. Molecular generative models utilize independent single-target property prediction networks to discover novel molecules. We propose using multi-target networks …