Deep learning with differential Gaussian process flows

Pashupati Hegde; Markus Heinonen; Harri Lähdesmäki; Samuel Kaski

Deep learning with differential Gaussian process flows

Pashupati Hegde, Markus Heinonen, Harri Lähdesmäki, Samuel Kaski

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

18 Citations (Scopus)

122 Downloads (Pure)

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 state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

Original language	English
Title of host publication	The 22nd International Conference on Artificial Intelligence and Statistic
Publisher	JMLR
Pages	1-15
Number of pages	16
Volume	89
Publication status	Published - Apr 2019
MoE publication type	A4 Conference publication
Event	International Conference on Artificial Intelligence and Statistics - Naha, Japan Duration: 16 Apr 2019 → 18 Apr 2019 Conference number: 22

Publication series

Name	Proceedings of Machine Learning Research
Publisher	PMLR
Volume	89
ISSN (Electronic)	2640-3498

Conference

Conference	International Conference on Artificial Intelligence and Statistics
Abbreviated title	AISTATS
Country/Territory	Japan
City	Naha
Period	16/04/2019 → 18/04/2019

Keywords

gaussian process
Bayesian methods

Access to Document

hegde19aAccepted author manuscript, 8.83 MB

https://proceedings.mlr.press/v89/hegde19a.html

Cite this

@inproceedings{800994a5a0814cacbf6a2ca49a218cef,

title = "Deep learning with differential Gaussian process flows",

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 state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks",

keywords = "gaussian process, Bayesian methods",

author = "Pashupati Hegde and Markus Heinonen and Harri L{\"a}hdesm{\"a}ki and Samuel Kaski",

year = "2019",

month = apr,

language = "English",

volume = "89",

series = "Proceedings of Machine Learning Research",

publisher = "JMLR",

pages = "1--15",

booktitle = "The 22nd International Conference on Artificial Intelligence and Statistic",

address = "United States",

note = "International Conference on Artificial Intelligence and Statistics, AISTATS ; Conference date: 16-04-2019 Through 18-04-2019",

}

Hegde, P , Heinonen, M , Lähdesmäki, H & Kaski, S 2019, Deep learning with differential Gaussian process flows. in The 22nd International Conference on Artificial Intelligence and Statistic. vol. 89, Proceedings of Machine Learning Research, vol. 89, JMLR, pp. 1-15, International Conference on Artificial Intelligence and Statistics, Naha, Japan, 16/04/2019. <https://proceedings.mlr.press/v89/hegde19a.html>

Deep learning with differential Gaussian process flows. / Hegde, Pashupati ; Heinonen, Markus ; Lähdesmäki, Harri et al.
The 22nd International Conference on Artificial Intelligence and Statistic. Vol. 89 JMLR, 2019. p. 1-15 (Proceedings of Machine Learning Research; Vol. 89).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Deep learning with differential Gaussian process flows

AU - Hegde, Pashupati

AU - Heinonen, Markus

AU - Lähdesmäki, Harri

AU - Kaski, Samuel

N1 - Conference code: 22

PY - 2019/4

Y1 - 2019/4

N2 - 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 state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

AB - 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 state-of-the-art results that exceed the performance of deep Gaussian processes and neural networks

KW - gaussian process

KW - Bayesian methods

UR - https://www.scopus.com/pages/publications/85082538735

M3 - Conference article in proceedings

VL - 89

T3 - Proceedings of Machine Learning Research

SP - 1

EP - 15

BT - The 22nd International Conference on Artificial Intelligence and Statistic

PB - JMLR

T2 - International Conference on Artificial Intelligence and Statistics

Y2 - 16 April 2019 through 18 April 2019

ER -

Deep learning with differential Gaussian process flows

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Interactive machine learning from multiple biodata sources

White-boxed artificial intelligence

Next-generation statistical learning for synthetic enzyme engineering

Science-IT

Cite this

Deep learning with differential Gaussian process flows

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Interactive machine learning from multiple biodata sources

White-boxed artificial intelligence

Next-generation statistical learning for synthetic enzyme engineering

Equipment

Science-IT

Cite this