Deep learning with differential Gaussian process flows

Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski
; Proceedings of Machine Learning Research, PMLR 89:1812-1821, 2019.

Abstract

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 the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate excellent results as compared to deep Gaussian processes and Bayesian neural networks.

Cite this Paper


BibTeX
@InProceedings{pmlr-v89-hegde19a, title = {Deep learning with differential Gaussian process flows}, author = {Hegde, Pashupati and Heinonen, Markus and L\"ahdesm\"aki, Harri and Kaski, Samuel}, booktitle = {Proceedings of Machine Learning Research}, pages = {1812--1821}, year = {2019}, editor = {Kamalika Chaudhuri and Masashi Sugiyama}, volume = {89}, series = {Proceedings of Machine Learning Research}, address = {}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/hegde19a/hegde19a.pdf}, url = {http://proceedings.mlr.press/v89/hegde19a.html}, abstract = {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 the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate excellent results as compared to deep Gaussian processes and Bayesian neural networks.} }
Endnote
%0 Conference Paper %T Deep learning with differential Gaussian process flows %A Pashupati Hegde %A Markus Heinonen %A Harri Lähdesmäki %A Samuel Kaski %B Proceedings of Machine Learning Research %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-hegde19a %I PMLR %J Proceedings of Machine Learning Research %P 1812--1821 %U http://proceedings.mlr.press %V 89 %W PMLR %X 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 the warping of inputs through infinitely deep, but infinitesimal, differential fields, that generalise discrete layers into a dynamical system. We demonstrate excellent results as compared to deep Gaussian processes and Bayesian neural networks.
APA
Hegde, P., Heinonen, M., Lähdesmäki, H. & Kaski, S.. (2019). Deep learning with differential Gaussian process flows. Proceedings of Machine Learning Research, in PMLR 89:1812-1821

Related Material