5 papers
Continuous-Time Model-Based Reinforcement Learning
Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki
Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in contin…
ODEVAE: Deep generative second order ODEs with Bayesian neural networks
Çağatay Yıldız, Markus Heinonen, Harri Lähdesmäki
We present Ordinary Differential Equation Variational Auto-Encoder (ODEVAE), a latent second order ODE model for high-dimensional sequential data. Leveraging the advances in de…
Learning Stochastic Differential Equations With Gaussian Processes Without Gradient Matching
Cagatay Yildiz, Markus Heinonen, Jukka Intosalmi +2
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 distr…
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
Umut Şimşekli, Çağatay Yıldız, Thanh Huy Nguyen +2
Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence…
Learning unknown ODE models with Gaussian processes
Markus Heinonen, Cagatay Yildiz, Henrik Mannerström +2
In conventional ODE modelling coefficients of an equation driving the system state forward in time are estimated. However, for many complex systems it is practically impossible to…