Learning Generative Models using Denoising Density Estimators Article Swipe

PDF

Siavash Arjomand Bigdeli , Geng Lin , Tiziano Portenier , L. A. Dunbar , Matthias Zwicker ·

YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2001.02728

Learning probabilistic models that can estimate the density of a given set of samples, and generate samples from that density, is one of the fundamental challenges in unsupervised machine learning. We introduce a new generative model based on denoising density estimators (DDEs), which are scalar functions parameterized by neural networks, that are efficiently trained to represent kernel density estimators of the data. Leveraging DDEs, our main contribution is a novel technique to obtain generative models by minimizing the KL-divergence directly. We prove that our algorithm for obtaining generative models is guaranteed to converge to the correct solution. Our approach does not require specific network architecture as in normalizing flows, nor use ordinary differential equation solvers as in continuous normalizing flows. Experimental results demonstrate substantial improvement in density estimation and competitive performance in generative model training.

Related Topics

Density Estimation

Computer Science

Machine Learning

Artificial Intelligence

Concepts

Estimator Kernel density estimation Density estimation Computer science Kernel (algebra) Artificial neural network Parameterized complexity Divergence (linguistics) Generative model Machine learning Artificial intelligence Scalar (mathematics) Applied mathematics Generative grammar Algorithm Mathematical optimization Mathematics Statistics Combinatorics Philosophy Geometry Linguistics

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2001.02728
PDF: https://arxiv.org/pdf/2001.02728
OA Status: green
Cited By: 4
Related Works: 10
OpenAlex ID: https://openalex.org/W4386480433

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4386480433

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2001.02728

Digital Object Identifier
Title: Learning Generative Models using Denoising Density Estimators

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2020

Year of publication
Publication date: 2020-01-08

Full publication date if available
Authors: Siavash Arjomand Bigdeli, Geng Lin, Tiziano Portenier, L. A. Dunbar, Matthias Zwicker

List of authors in order
Landing page: https://arxiv.org/abs/2001.02728

Publisher landing page
PDF URL: https://arxiv.org/pdf/2001.02728

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2001.02728

Direct OA link when available
Concepts: Estimator, Kernel density estimation, Density estimation, Computer science, Kernel (algebra), Artificial neural network, Parameterized complexity, Divergence (linguistics), Generative model, Machine learning, Artificial intelligence, Scalar (mathematics), Applied mathematics, Generative grammar, Algorithm, Mathematical optimization, Mathematics, Statistics, Combinatorics, Philosophy, Geometry, Linguistics

Top concepts (fields/topics) attached by OpenAlex
Cited by: 4

Total citation count in OpenAlex
Citations by year (recent): 2024: 1, 2022: 2, 2021: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4386480433
doi	https://doi.org/10.48550/arxiv.2001.02728
ids.doi	https://doi.org/10.48550/arxiv.2001.02728
ids.openalex	https://openalex.org/W4386480433
fwci
type	preprint
title	Learning Generative Models using Denoising Density Estimators
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T10775
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.996399998664856
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Generative Adversarial Networks and Image Synthesis
topics[1].id	https://openalex.org/T11309
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9767000079154968
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1711
topics[1].subfield.display_name	Signal Processing
topics[1].display_name	Music and Audio Processing
topics[2].id	https://openalex.org/T10320
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9729999899864197
topics[2].domain.id	https://openalex.org/domains/3
topics[2].domain.display_name	Physical Sciences
topics[2].subfield.id	https://openalex.org/subfields/1702
topics[2].subfield.display_name	Artificial Intelligence
topics[2].display_name	Neural Networks and Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C185429906
concepts[0].level	2
concepts[0].score	0.7337956428527832
concepts[0].wikidata	https://www.wikidata.org/wiki/Q1130160
concepts[0].display_name	Estimator
concepts[1].id	https://openalex.org/C71134354
concepts[1].level	3
concepts[1].score	0.6401278376579285
concepts[1].wikidata	https://www.wikidata.org/wiki/Q458825
concepts[1].display_name	Kernel density estimation
concepts[2].id	https://openalex.org/C189508267
concepts[2].level	3
concepts[2].score	0.6058013439178467
concepts[2].wikidata	https://www.wikidata.org/wiki/Q17088227
concepts[2].display_name	Density estimation
concepts[3].id	https://openalex.org/C41008148
concepts[3].level	0
concepts[3].score	0.6040161848068237
concepts[3].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[3].display_name	Computer science
concepts[4].id	https://openalex.org/C74193536
concepts[4].level	2
concepts[4].score	0.5187711715698242
concepts[4].wikidata	https://www.wikidata.org/wiki/Q574844
concepts[4].display_name	Kernel (algebra)
concepts[5].id	https://openalex.org/C50644808
concepts[5].level	2
concepts[5].score	0.5141084790229797
concepts[5].wikidata	https://www.wikidata.org/wiki/Q192776
concepts[5].display_name	Artificial neural network
concepts[6].id	https://openalex.org/C165464430
concepts[6].level	2
concepts[6].score	0.5137292146682739
concepts[6].wikidata	https://www.wikidata.org/wiki/Q1570441
concepts[6].display_name	Parameterized complexity
concepts[7].id	https://openalex.org/C207390915
concepts[7].level	2
concepts[7].score	0.5058769583702087
concepts[7].wikidata	https://www.wikidata.org/wiki/Q1230525
concepts[7].display_name	Divergence (linguistics)
concepts[8].id	https://openalex.org/C167966045
concepts[8].level	3
concepts[8].score	0.4867587089538574
concepts[8].wikidata	https://www.wikidata.org/wiki/Q5532625
concepts[8].display_name	Generative model
concepts[9].id	https://openalex.org/C119857082
concepts[9].level	1
concepts[9].score	0.4774501919746399
concepts[9].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[9].display_name	Machine learning
concepts[10].id	https://openalex.org/C154945302
concepts[10].level	1
concepts[10].score	0.47301653027534485
concepts[10].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[10].display_name	Artificial intelligence
concepts[11].id	https://openalex.org/C57691317
concepts[11].level	2
concepts[11].score	0.4184778332710266
concepts[11].wikidata	https://www.wikidata.org/wiki/Q1289248
concepts[11].display_name	Scalar (mathematics)
concepts[12].id	https://openalex.org/C28826006
concepts[12].level	1
concepts[12].score	0.4074234366416931
concepts[12].wikidata	https://www.wikidata.org/wiki/Q33521
concepts[12].display_name	Applied mathematics
concepts[13].id	https://openalex.org/C39890363
concepts[13].level	2
concepts[13].score	0.4009261727333069
concepts[13].wikidata	https://www.wikidata.org/wiki/Q36108
concepts[13].display_name	Generative grammar
concepts[14].id	https://openalex.org/C11413529
concepts[14].level	1
concepts[14].score	0.38106974959373474
concepts[14].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[14].display_name	Algorithm
concepts[15].id	https://openalex.org/C126255220
concepts[15].level	1
concepts[15].score	0.3554191291332245
concepts[15].wikidata	https://www.wikidata.org/wiki/Q141495
concepts[15].display_name	Mathematical optimization
concepts[16].id	https://openalex.org/C33923547
concepts[16].level	0
concepts[16].score	0.32150059938430786
concepts[16].wikidata	https://www.wikidata.org/wiki/Q395
concepts[16].display_name	Mathematics
concepts[17].id	https://openalex.org/C105795698
concepts[17].level	1
concepts[17].score	0.08419546484947205
concepts[17].wikidata	https://www.wikidata.org/wiki/Q12483
concepts[17].display_name	Statistics
concepts[18].id	https://openalex.org/C114614502
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q76592
concepts[18].display_name	Combinatorics
concepts[19].id	https://openalex.org/C138885662
concepts[19].level	0
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q5891
concepts[19].display_name	Philosophy
concepts[20].id	https://openalex.org/C2524010
concepts[20].level	1
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q8087
concepts[20].display_name	Geometry
concepts[21].id	https://openalex.org/C41895202
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q8162
concepts[21].display_name	Linguistics
keywords[0].id	https://openalex.org/keywords/estimator
keywords[0].score	0.7337956428527832
keywords[0].display_name	Estimator
keywords[1].id	https://openalex.org/keywords/kernel-density-estimation
keywords[1].score	0.6401278376579285
keywords[1].display_name	Kernel density estimation
keywords[2].id	https://openalex.org/keywords/density-estimation
keywords[2].score	0.6058013439178467
keywords[2].display_name	Density estimation
keywords[3].id	https://openalex.org/keywords/computer-science
keywords[3].score	0.6040161848068237
keywords[3].display_name	Computer science
keywords[4].id	https://openalex.org/keywords/kernel
keywords[4].score	0.5187711715698242
keywords[4].display_name	Kernel (algebra)
keywords[5].id	https://openalex.org/keywords/artificial-neural-network
keywords[5].score	0.5141084790229797
keywords[5].display_name	Artificial neural network
keywords[6].id	https://openalex.org/keywords/parameterized-complexity
keywords[6].score	0.5137292146682739
keywords[6].display_name	Parameterized complexity
keywords[7].id	https://openalex.org/keywords/divergence
keywords[7].score	0.5058769583702087
keywords[7].display_name	Divergence (linguistics)
keywords[8].id	https://openalex.org/keywords/generative-model
keywords[8].score	0.4867587089538574
keywords[8].display_name	Generative model
keywords[9].id	https://openalex.org/keywords/machine-learning
keywords[9].score	0.4774501919746399
keywords[9].display_name	Machine learning
keywords[10].id	https://openalex.org/keywords/artificial-intelligence
keywords[10].score	0.47301653027534485
keywords[10].display_name	Artificial intelligence
keywords[11].id	https://openalex.org/keywords/scalar
keywords[11].score	0.4184778332710266
keywords[11].display_name	Scalar (mathematics)
keywords[12].id	https://openalex.org/keywords/applied-mathematics
keywords[12].score	0.4074234366416931
keywords[12].display_name	Applied mathematics
keywords[13].id	https://openalex.org/keywords/generative-grammar
keywords[13].score	0.4009261727333069
keywords[13].display_name	Generative grammar
keywords[14].id	https://openalex.org/keywords/algorithm
keywords[14].score	0.38106974959373474
keywords[14].display_name	Algorithm
keywords[15].id	https://openalex.org/keywords/mathematical-optimization
keywords[15].score	0.3554191291332245
keywords[15].display_name	Mathematical optimization
keywords[16].id	https://openalex.org/keywords/mathematics
keywords[16].score	0.32150059938430786
keywords[16].display_name	Mathematics
keywords[17].id	https://openalex.org/keywords/statistics
keywords[17].score	0.08419546484947205
keywords[17].display_name	Statistics
language	en
locations[0].id	pmh:oai:arXiv.org:2001.02728
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2001.02728
locations[0].version	submittedVersion
locations[0].raw_type
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2001.02728
locations[1].id	doi:10.48550/arxiv.2001.02728
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2001.02728
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5024315163
authorships[0].author.orcid	https://orcid.org/0000-0003-2569-6473
authorships[0].author.display_name	Siavash Arjomand Bigdeli
authorships[0].author_position	first
authorships[0].raw_author_name	Bigdeli, Siavash A.
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5045682736
authorships[1].author.orcid	https://orcid.org/0009-0001-6718-6757
authorships[1].author.display_name	Geng Lin
authorships[1].author_position	middle
authorships[1].raw_author_name	Lin, Geng
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5036633606
authorships[2].author.orcid	https://orcid.org/0000-0003-1766-1705
authorships[2].author.display_name	Tiziano Portenier
authorships[2].author_position	middle
authorships[2].raw_author_name	Portenier, Tiziano
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5118899624
authorships[3].author.orcid	https://orcid.org/0009-0000-3379-6170
authorships[3].author.display_name	L. A. Dunbar
authorships[3].author_position	middle
authorships[3].raw_author_name	Dunbar, L. Andrea
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5014079156
authorships[4].author.orcid	https://orcid.org/0000-0001-8630-5515
authorships[4].author.display_name	Matthias Zwicker
authorships[4].author_position	last
authorships[4].raw_author_name	Zwicker, Matthias
authorships[4].is_corresponding	False
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2001.02728
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Learning Generative Models using Denoising Density Estimators
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T10775
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.996399998664856
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Generative Adversarial Networks and Image Synthesis
related_works	https://openalex.org/W4365211920, https://openalex.org/W3014948380, https://openalex.org/W1482149696, https://openalex.org/W2583877436, https://openalex.org/W4380551139, https://openalex.org/W4317695495, https://openalex.org/W4287117424, https://openalex.org/W4387506531, https://openalex.org/W4238433571, https://openalex.org/W3174044702
cited_by_count	4
counts_by_year[0].year	2024
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2022
counts_by_year[1].cited_by_count	2
counts_by_year[2].year	2021
counts_by_year[2].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2001.02728
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2001.02728
best_oa_location.version	submittedVersion
best_oa_location.raw_type
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2001.02728
primary_location.id	pmh:oai:arXiv.org:2001.02728
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2001.02728
primary_location.version	submittedVersion
primary_location.raw_type
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2001.02728
publication_date	2020-01-08
publication_year	2020
referenced_works_count	0
abstract_inverted_index.a	9, 32, 68
abstract_inverted_index.We	30, 80
abstract_inverted_index.as	105, 115
abstract_inverted_index.by	47, 75
abstract_inverted_index.in	26, 106, 116, 125, 131
abstract_inverted_index.is	20, 67, 89
abstract_inverted_index.of	8, 12, 22, 59
abstract_inverted_index.on	37
abstract_inverted_index.to	54, 71, 91, 93
abstract_inverted_index.Our	97
abstract_inverted_index.and	14, 128
abstract_inverted_index.are	43, 51
abstract_inverted_index.can	4
abstract_inverted_index.for	85
abstract_inverted_index.new	33
abstract_inverted_index.nor	109
abstract_inverted_index.not	100
abstract_inverted_index.one	21
abstract_inverted_index.our	64, 83
abstract_inverted_index.set	11
abstract_inverted_index.the	6, 23, 60, 77, 94
abstract_inverted_index.use	110
abstract_inverted_index.does	99
abstract_inverted_index.from	17
abstract_inverted_index.main	65
abstract_inverted_index.that	3, 18, 50, 82
abstract_inverted_index.DDEs,	63
abstract_inverted_index.based	36
abstract_inverted_index.data.	61
abstract_inverted_index.given	10
abstract_inverted_index.model	35, 133
abstract_inverted_index.novel	69
abstract_inverted_index.prove	81
abstract_inverted_index.which	42
abstract_inverted_index.flows,	108
abstract_inverted_index.flows.	119
abstract_inverted_index.kernel	56
abstract_inverted_index.models	2, 74, 88
abstract_inverted_index.neural	48
abstract_inverted_index.obtain	72
abstract_inverted_index.scalar	44
abstract_inverted_index.(DDEs),	41
abstract_inverted_index.correct	95
abstract_inverted_index.density	7, 39, 57, 126
abstract_inverted_index.machine	28
abstract_inverted_index.network	103
abstract_inverted_index.require	101
abstract_inverted_index.results	121
abstract_inverted_index.samples	16
abstract_inverted_index.solvers	114
abstract_inverted_index.trained	53
abstract_inverted_index.Learning	0
abstract_inverted_index.approach	98
abstract_inverted_index.converge	92
abstract_inverted_index.density,	19
abstract_inverted_index.equation	113
abstract_inverted_index.estimate	5
abstract_inverted_index.generate	15
abstract_inverted_index.ordinary	111
abstract_inverted_index.samples,	13
abstract_inverted_index.specific	102
abstract_inverted_index.algorithm	84
abstract_inverted_index.denoising	38
abstract_inverted_index.directly.	79
abstract_inverted_index.functions	45
abstract_inverted_index.introduce	31
abstract_inverted_index.learning.	29
abstract_inverted_index.networks,	49
abstract_inverted_index.obtaining	86
abstract_inverted_index.represent	55
abstract_inverted_index.solution.	96
abstract_inverted_index.technique	70
abstract_inverted_index.training.	134
abstract_inverted_index.Leveraging	62
abstract_inverted_index.challenges	25
abstract_inverted_index.continuous	117
abstract_inverted_index.estimation	127
abstract_inverted_index.estimators	40, 58
abstract_inverted_index.generative	34, 73, 87, 132
abstract_inverted_index.guaranteed	90
abstract_inverted_index.minimizing	76
abstract_inverted_index.competitive	129
abstract_inverted_index.demonstrate	122
abstract_inverted_index.efficiently	52
abstract_inverted_index.fundamental	24
abstract_inverted_index.improvement	124
abstract_inverted_index.normalizing	107, 118
abstract_inverted_index.performance	130
abstract_inverted_index.substantial	123
abstract_inverted_index.Experimental	120
abstract_inverted_index.architecture	104
abstract_inverted_index.contribution	66
abstract_inverted_index.differential	112
abstract_inverted_index.unsupervised	27
abstract_inverted_index.KL-divergence	78
abstract_inverted_index.parameterized	46
abstract_inverted_index.probabilistic	1
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	5
citation_normalized_percentile