Deep Stochastic Processes via Functional Markov Transition Operators
Abstract
We introduce Markov Neural Processes (MNPs), a new class of Stochastic Processes (SPs) which are constructed by stacking sequences of neural parameterised Markov transition operators in function space. We prove that these Markov transition operators can preserve the exchangeability and consistency of SPs. Therefore, the proposed iterative construction adds substantial flexibility and expressivity to the original framework of Neural Processes (NPs) without compromising consistency or adding restrictions. Our experiments demonstrate clear advantages of MNPs over baseline models on a variety of tasks.
Cite
Text
Xu et al. "Deep Stochastic Processes via Functional Markov Transition Operators." Neural Information Processing Systems, 2023.Markdown
[Xu et al. "Deep Stochastic Processes via Functional Markov Transition Operators." Neural Information Processing Systems, 2023.](https://mlanthology.org/neurips/2023/xu2023neurips-deep/)BibTeX
@inproceedings{xu2023neurips-deep,
title = {{Deep Stochastic Processes via Functional Markov Transition Operators}},
author = {Xu, Jin and Dupont, Emilien and Märtens, Kaspar and Rainforth, Thomas and Teh, Yee Whye},
booktitle = {Neural Information Processing Systems},
year = {2023},
url = {https://mlanthology.org/neurips/2023/xu2023neurips-deep/}
}