Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler Article Swipe
Jianwen Xie
,
Zilong Zheng
,
Ping Li
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2012.14936
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2012.14936
Due to the intractable partition function, training energy-based models (EBMs) by maximum likelihood requires Markov chain Monte Carlo (MCMC) sampling to approximate the gradient of the Kullback-Leibler divergence between data and model distributions. However, it is non-trivial to sample from an EBM because of the difficulty of mixing between modes. In this paper, we propose to learn a variational auto-encoder (VAE) to initialize the finite-step MCMC, such as Langevin dynamics that is derived from the energy function, for efficient amortized sampling of the EBM. With these amortized MCMC samples, the EBM can be trained by maximum likelihood, which follows an "analysis by synthesis" scheme; while the VAE learns from these MCMC samples via variational Bayes. We call this joint training algorithm the variational MCMC teaching, in which the VAE chases the EBM toward data distribution. We interpret the learning algorithm as a dynamic alternating projection in the context of information geometry. Our proposed models can generate samples comparable to GANs and EBMs. Additionally, we demonstrate that our model can learn effective probabilistic distribution toward supervised conditional learning tasks.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2012.14936
- https://arxiv.org/pdf/2012.14936
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3173214724
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3173214724Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2012.14936Digital Object Identifier
- Title
-
Learning Energy-Based Model with Variational Auto-Encoder as Amortized SamplerWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-12-29Full publication date if available
- Authors
-
Jianwen Xie, Zilong Zheng, Ping LiList of authors in order
- Landing page
-
https://arxiv.org/abs/2012.14936Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2012.14936Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2012.14936Direct OA link when available
- Concepts
-
Markov chain Monte Carlo, Computer science, Algorithm, Prior probability, Kullback–Leibler divergence, Bayes' theorem, Context (archaeology), Sampling (signal processing), Bayesian probability, Mathematics, Artificial intelligence, Computer vision, Paleontology, Filter (signal processing), BiologyTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2021: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3173214724 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2012.14936 |
| ids.doi | https://doi.org/10.48550/arxiv.2012.14936 |
| ids.mag | 3173214724 |
| ids.openalex | https://openalex.org/W3173214724 |
| fwci | 0.10496732 |
| type | preprint |
| title | Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler |
| 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 | 0.9614999890327454 |
| 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/T11948 |
| topics[1].field.id | https://openalex.org/fields/25 |
| topics[1].field.display_name | Materials Science |
| topics[1].score | 0.9168999791145325 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2505 |
| topics[1].subfield.display_name | Materials Chemistry |
| topics[1].display_name | Machine Learning in Materials Science |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C111350023 |
| concepts[0].level | 3 |
| concepts[0].score | 0.9161704778671265 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1191869 |
| concepts[0].display_name | Markov chain Monte Carlo |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.5040756464004517 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C11413529 |
| concepts[2].level | 1 |
| concepts[2].score | 0.48550963401794434 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[2].display_name | Algorithm |
| concepts[3].id | https://openalex.org/C177769412 |
| concepts[3].level | 3 |
| concepts[3].score | 0.4723832607269287 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q278090 |
| concepts[3].display_name | Prior probability |
| concepts[4].id | https://openalex.org/C171752962 |
| concepts[4].level | 2 |
| concepts[4].score | 0.4627509117126465 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q255166 |
| concepts[4].display_name | Kullback–Leibler divergence |
| concepts[5].id | https://openalex.org/C207201462 |
| concepts[5].level | 3 |
| concepts[5].score | 0.4499286115169525 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q182505 |
| concepts[5].display_name | Bayes' theorem |
| concepts[6].id | https://openalex.org/C2779343474 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4267820715904236 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q3109175 |
| concepts[6].display_name | Context (archaeology) |
| concepts[7].id | https://openalex.org/C140779682 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4175175428390503 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q210868 |
| concepts[7].display_name | Sampling (signal processing) |
| concepts[8].id | https://openalex.org/C107673813 |
| concepts[8].level | 2 |
| concepts[8].score | 0.40002748370170593 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q812534 |
| concepts[8].display_name | Bayesian probability |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.38958466053009033 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C154945302 |
| concepts[10].level | 1 |
| concepts[10].score | 0.38397216796875 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[10].display_name | Artificial intelligence |
| concepts[11].id | https://openalex.org/C31972630 |
| concepts[11].level | 1 |
| concepts[11].score | 0.12253528833389282 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[11].display_name | Computer vision |
| concepts[12].id | https://openalex.org/C151730666 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q7205 |
| concepts[12].display_name | Paleontology |
| concepts[13].id | https://openalex.org/C106131492 |
| concepts[13].level | 2 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q3072260 |
| concepts[13].display_name | Filter (signal processing) |
| concepts[14].id | https://openalex.org/C86803240 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q420 |
| concepts[14].display_name | Biology |
| keywords[0].id | https://openalex.org/keywords/markov-chain-monte-carlo |
| keywords[0].score | 0.9161704778671265 |
| keywords[0].display_name | Markov chain Monte Carlo |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.5040756464004517 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/algorithm |
| keywords[2].score | 0.48550963401794434 |
| keywords[2].display_name | Algorithm |
| keywords[3].id | https://openalex.org/keywords/prior-probability |
| keywords[3].score | 0.4723832607269287 |
| keywords[3].display_name | Prior probability |
| keywords[4].id | https://openalex.org/keywords/kullback–leibler-divergence |
| keywords[4].score | 0.4627509117126465 |
| keywords[4].display_name | Kullback–Leibler divergence |
| keywords[5].id | https://openalex.org/keywords/bayes-theorem |
| keywords[5].score | 0.4499286115169525 |
| keywords[5].display_name | Bayes' theorem |
| keywords[6].id | https://openalex.org/keywords/context |
| keywords[6].score | 0.4267820715904236 |
| keywords[6].display_name | Context (archaeology) |
| keywords[7].id | https://openalex.org/keywords/sampling |
| keywords[7].score | 0.4175175428390503 |
| keywords[7].display_name | Sampling (signal processing) |
| keywords[8].id | https://openalex.org/keywords/bayesian-probability |
| keywords[8].score | 0.40002748370170593 |
| keywords[8].display_name | Bayesian probability |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.38958466053009033 |
| keywords[9].display_name | Mathematics |
| keywords[10].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[10].score | 0.38397216796875 |
| keywords[10].display_name | Artificial intelligence |
| keywords[11].id | https://openalex.org/keywords/computer-vision |
| keywords[11].score | 0.12253528833389282 |
| keywords[11].display_name | Computer vision |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2012.14936 |
| 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/2012.14936 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| 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/2012.14936 |
| locations[1].id | doi:10.48550/arxiv.2012.14936 |
| 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-journal |
| 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.2012.14936 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102966958 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-6818-7444 |
| authorships[0].author.display_name | Jianwen Xie |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I98301712 |
| authorships[0].affiliations[0].raw_affiliation_string | Baidu Research; |
| authorships[0].institutions[0].id | https://openalex.org/I98301712 |
| authorships[0].institutions[0].ror | https://ror.org/03vs3wt56 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I98301712 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | Baidu (China) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jianwen Xie |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Baidu Research; |
| authorships[1].author.id | https://openalex.org/A5056521090 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1219-5151 |
| authorships[1].author.display_name | Zilong Zheng |
| authorships[1].countries | CN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I98301712 |
| authorships[1].affiliations[0].raw_affiliation_string | Baidu Research; |
| authorships[1].institutions[0].id | https://openalex.org/I98301712 |
| authorships[1].institutions[0].ror | https://ror.org/03vs3wt56 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I98301712 |
| authorships[1].institutions[0].country_code | CN |
| authorships[1].institutions[0].display_name | Baidu (China) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zilong Zheng |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Baidu Research; |
| authorships[2].author.id | https://openalex.org/A5100435494 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-1503-0240 |
| authorships[2].author.display_name | Ping Li |
| authorships[2].countries | CN |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I98301712 |
| authorships[2].affiliations[0].raw_affiliation_string | Baidu Research; |
| authorships[2].institutions[0].id | https://openalex.org/I98301712 |
| authorships[2].institutions[0].ror | https://ror.org/03vs3wt56 |
| authorships[2].institutions[0].type | company |
| authorships[2].institutions[0].lineage | https://openalex.org/I98301712 |
| authorships[2].institutions[0].country_code | CN |
| authorships[2].institutions[0].display_name | Baidu (China) |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Ping Li |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Baidu Research; |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2012.14936 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2021-07-05T00:00:00 |
| display_name | Learning Energy-Based Model with Variational Auto-Encoder as Amortized Sampler |
| has_fulltext | False |
| 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 | 0.9614999890327454 |
| 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/W4283770175, https://openalex.org/W2343819364, https://openalex.org/W2133205540, https://openalex.org/W2562263695, https://openalex.org/W2135187896, https://openalex.org/W2147201983, https://openalex.org/W2015518264, https://openalex.org/W2795035211, https://openalex.org/W2160108762, https://openalex.org/W1718066205 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2021 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2012.14936 |
| 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/2012.14936 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2012.14936 |
| primary_location.id | pmh:oai:arXiv.org:2012.14936 |
| 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/2012.14936 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| 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/2012.14936 |
| publication_date | 2020-12-29 |
| publication_year | 2020 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 57, 141 |
| abstract_inverted_index.In | 50 |
| abstract_inverted_index.We | 115, 135 |
| abstract_inverted_index.an | 40, 99 |
| abstract_inverted_index.as | 67, 140 |
| abstract_inverted_index.be | 92 |
| abstract_inverted_index.by | 10, 94, 101 |
| abstract_inverted_index.in | 125, 145 |
| abstract_inverted_index.is | 35, 71 |
| abstract_inverted_index.it | 34 |
| abstract_inverted_index.of | 24, 43, 46, 81, 148 |
| abstract_inverted_index.to | 1, 20, 37, 55, 61, 158 |
| abstract_inverted_index.we | 53, 163 |
| abstract_inverted_index.Due | 0 |
| abstract_inverted_index.EBM | 41, 90, 131 |
| abstract_inverted_index.Our | 151 |
| abstract_inverted_index.VAE | 106, 128 |
| abstract_inverted_index.and | 30, 160 |
| abstract_inverted_index.can | 91, 154, 168 |
| abstract_inverted_index.for | 77 |
| abstract_inverted_index.our | 166 |
| abstract_inverted_index.the | 2, 22, 25, 44, 63, 74, 82, 89, 105, 121, 127, 130, 137, 146 |
| abstract_inverted_index.via | 112 |
| abstract_inverted_index.EBM. | 83 |
| abstract_inverted_index.GANs | 159 |
| abstract_inverted_index.MCMC | 87, 110, 123 |
| abstract_inverted_index.With | 84 |
| abstract_inverted_index.call | 116 |
| abstract_inverted_index.data | 29, 133 |
| abstract_inverted_index.from | 39, 73, 108 |
| abstract_inverted_index.such | 66 |
| abstract_inverted_index.that | 70, 165 |
| abstract_inverted_index.this | 51, 117 |
| abstract_inverted_index.(VAE) | 60 |
| abstract_inverted_index.Carlo | 17 |
| abstract_inverted_index.EBMs. | 161 |
| abstract_inverted_index.MCMC, | 65 |
| abstract_inverted_index.Monte | 16 |
| abstract_inverted_index.chain | 15 |
| abstract_inverted_index.joint | 118 |
| abstract_inverted_index.learn | 56, 169 |
| abstract_inverted_index.model | 31, 167 |
| abstract_inverted_index.these | 85, 109 |
| abstract_inverted_index.which | 97, 126 |
| abstract_inverted_index.while | 104 |
| abstract_inverted_index.(EBMs) | 9 |
| abstract_inverted_index.(MCMC) | 18 |
| abstract_inverted_index.Bayes. | 114 |
| abstract_inverted_index.Markov | 14 |
| abstract_inverted_index.chases | 129 |
| abstract_inverted_index.energy | 75 |
| abstract_inverted_index.learns | 107 |
| abstract_inverted_index.mixing | 47 |
| abstract_inverted_index.models | 8, 153 |
| abstract_inverted_index.modes. | 49 |
| abstract_inverted_index.paper, | 52 |
| abstract_inverted_index.sample | 38 |
| abstract_inverted_index.tasks. | 177 |
| abstract_inverted_index.toward | 132, 173 |
| abstract_inverted_index.because | 42 |
| abstract_inverted_index.between | 28, 48 |
| abstract_inverted_index.context | 147 |
| abstract_inverted_index.derived | 72 |
| abstract_inverted_index.dynamic | 142 |
| abstract_inverted_index.follows | 98 |
| abstract_inverted_index.maximum | 11, 95 |
| abstract_inverted_index.propose | 54 |
| abstract_inverted_index.samples | 111, 156 |
| abstract_inverted_index.scheme; | 103 |
| abstract_inverted_index.trained | 93 |
| abstract_inverted_index.However, | 33 |
| abstract_inverted_index.Langevin | 68 |
| abstract_inverted_index.dynamics | 69 |
| abstract_inverted_index.generate | 155 |
| abstract_inverted_index.gradient | 23 |
| abstract_inverted_index.learning | 138, 176 |
| abstract_inverted_index.proposed | 152 |
| abstract_inverted_index.requires | 13 |
| abstract_inverted_index.samples, | 88 |
| abstract_inverted_index.sampling | 19, 80 |
| abstract_inverted_index.training | 6, 119 |
| abstract_inverted_index."analysis | 100 |
| abstract_inverted_index.algorithm | 120, 139 |
| abstract_inverted_index.amortized | 79, 86 |
| abstract_inverted_index.effective | 170 |
| abstract_inverted_index.efficient | 78 |
| abstract_inverted_index.function, | 5, 76 |
| abstract_inverted_index.geometry. | 150 |
| abstract_inverted_index.interpret | 136 |
| abstract_inverted_index.partition | 4 |
| abstract_inverted_index.teaching, | 124 |
| abstract_inverted_index.comparable | 157 |
| abstract_inverted_index.difficulty | 45 |
| abstract_inverted_index.divergence | 27 |
| abstract_inverted_index.initialize | 62 |
| abstract_inverted_index.likelihood | 12 |
| abstract_inverted_index.projection | 144 |
| abstract_inverted_index.supervised | 174 |
| abstract_inverted_index.synthesis" | 102 |
| abstract_inverted_index.alternating | 143 |
| abstract_inverted_index.approximate | 21 |
| abstract_inverted_index.conditional | 175 |
| abstract_inverted_index.demonstrate | 164 |
| abstract_inverted_index.finite-step | 64 |
| abstract_inverted_index.information | 149 |
| abstract_inverted_index.intractable | 3 |
| abstract_inverted_index.likelihood, | 96 |
| abstract_inverted_index.non-trivial | 36 |
| abstract_inverted_index.variational | 58, 113, 122 |
| abstract_inverted_index.auto-encoder | 59 |
| abstract_inverted_index.distribution | 172 |
| abstract_inverted_index.energy-based | 7 |
| abstract_inverted_index.Additionally, | 162 |
| abstract_inverted_index.distribution. | 134 |
| abstract_inverted_index.probabilistic | 171 |
| abstract_inverted_index.distributions. | 32 |
| abstract_inverted_index.Kullback-Leibler | 26 |
| cited_by_percentile_year.max | 93 |
| cited_by_percentile_year.min | 89 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/7 |
| sustainable_development_goals[0].score | 0.8899999856948853 |
| sustainable_development_goals[0].display_name | Affordable and clean energy |
| citation_normalized_percentile.value | 0.46371548 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |