Latent Space Energy-based Neural ODEs Article Swipe
Sheng Cheng
,
Deqian Kong
,
Jianwen Xie
,
Kookjin Lee
,
Ying Wu
,
Yezhou Yang
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.03845
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2409.03845
This paper introduces novel deep dynamical models designed to represent continuous-time sequences. Our approach employs a neural emission model to generate each data point in the time series through a non-linear transformation of a latent state vector. The evolution of these latent states is implicitly defined by a neural ordinary differential equation (ODE), with the initial state drawn from an informative prior distribution parameterized by an Energy-based model (EBM). This framework is extended to disentangle dynamic states from underlying static factors of variation, represented as time-invariant variables in the latent space. We train the model using maximum likelihood estimation with Markov chain Monte Carlo (MCMC) in an end-to-end manner. Experimental results on oscillating systems, videos and real-world state sequences (MuJoCo) demonstrate that our model with the learnable energy-based prior outperforms existing counterparts, and can generalize to new dynamic parameterization, enabling long-horizon predictions.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2409.03845
- https://arxiv.org/pdf/2409.03845
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4403585935
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4403585935Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2409.03845Digital Object Identifier
- Title
-
Latent Space Energy-based Neural ODEsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-09-05Full publication date if available
- Authors
-
Sheng Cheng, Deqian Kong, Jianwen Xie, Kookjin Lee, Ying Wu, Yezhou YangList of authors in order
- Landing page
-
https://arxiv.org/abs/2409.03845Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2409.03845Direct 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/2409.03845Direct OA link when available
- Concepts
-
Ode, Space (punctuation), Artificial neural network, Computer science, Energy (signal processing), Artificial intelligence, Mathematics, Applied mathematics, Statistics, Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4403585935 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2409.03845 |
| ids.doi | https://doi.org/10.48550/arxiv.2409.03845 |
| ids.openalex | https://openalex.org/W4403585935 |
| fwci | |
| type | preprint |
| title | Latent Space Energy-based Neural ODEs |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.7961999773979187 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Neural Networks and Applications |
| topics[1].id | https://openalex.org/T11326 |
| topics[1].field.id | https://openalex.org/fields/18 |
| topics[1].field.display_name | Decision Sciences |
| topics[1].score | 0.695900022983551 |
| topics[1].domain.id | https://openalex.org/domains/2 |
| topics[1].domain.display_name | Social Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1803 |
| topics[1].subfield.display_name | Management Science and Operations Research |
| topics[1].display_name | Stock Market Forecasting Methods |
| topics[2].id | https://openalex.org/T14339 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.6578999757766724 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Image Processing and 3D Reconstruction |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C34862557 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7356390357017517 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q178985 |
| concepts[0].display_name | Ode |
| concepts[1].id | https://openalex.org/C2778572836 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6456546187400818 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q380933 |
| concepts[1].display_name | Space (punctuation) |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.48160597681999207 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.47123751044273376 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C186370098 |
| concepts[4].level | 2 |
| concepts[4].score | 0.46875619888305664 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q442787 |
| concepts[4].display_name | Energy (signal processing) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.372804194688797 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C33923547 |
| concepts[6].level | 0 |
| concepts[6].score | 0.3171940743923187 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[6].display_name | Mathematics |
| concepts[7].id | https://openalex.org/C28826006 |
| concepts[7].level | 1 |
| concepts[7].score | 0.23942959308624268 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q33521 |
| concepts[7].display_name | Applied mathematics |
| concepts[8].id | https://openalex.org/C105795698 |
| concepts[8].level | 1 |
| concepts[8].score | 0.09817489981651306 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[8].display_name | Statistics |
| concepts[9].id | https://openalex.org/C111919701 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[9].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/ode |
| keywords[0].score | 0.7356390357017517 |
| keywords[0].display_name | Ode |
| keywords[1].id | https://openalex.org/keywords/space |
| keywords[1].score | 0.6456546187400818 |
| keywords[1].display_name | Space (punctuation) |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.48160597681999207 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.47123751044273376 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/energy |
| keywords[4].score | 0.46875619888305664 |
| keywords[4].display_name | Energy (signal processing) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.372804194688797 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/mathematics |
| keywords[6].score | 0.3171940743923187 |
| keywords[6].display_name | Mathematics |
| keywords[7].id | https://openalex.org/keywords/applied-mathematics |
| keywords[7].score | 0.23942959308624268 |
| keywords[7].display_name | Applied mathematics |
| keywords[8].id | https://openalex.org/keywords/statistics |
| keywords[8].score | 0.09817489981651306 |
| keywords[8].display_name | Statistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2409.03845 |
| 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/2409.03845 |
| 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/2409.03845 |
| locations[1].id | doi:10.48550/arxiv.2409.03845 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2409.03845 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5022492752 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7244-5998 |
| authorships[0].author.display_name | Sheng Cheng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Cheng, Sheng |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5084751425 |
| authorships[1].author.orcid | https://orcid.org/0009-0001-3581-8836 |
| authorships[1].author.display_name | Deqian Kong |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Kong, Deqian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102966958 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-6818-7444 |
| authorships[2].author.display_name | Jianwen Xie |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xie, Jianwen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5003125158 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-1557-5862 |
| authorships[3].author.display_name | Kookjin Lee |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lee, Kookjin |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5042765290 |
| authorships[4].author.orcid | https://orcid.org/0009-0000-6998-8924 |
| authorships[4].author.display_name | Ying Wu |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Wu, Ying Nian |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5102031937 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Yezhou Yang |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Yang, Yezhou |
| authorships[5].is_corresponding | False |
| 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/2409.03845 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Latent Space Energy-based Neural ODEs |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.7961999773979187 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Neural Networks and Applications |
| related_works | https://openalex.org/W2371448224, https://openalex.org/W3134495997, https://openalex.org/W2363680170, https://openalex.org/W2376428685, https://openalex.org/W4256082577, https://openalex.org/W625783435, https://openalex.org/W2048742619, https://openalex.org/W2384641672, https://openalex.org/W2742179975, https://openalex.org/W2362647823 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2409.03845 |
| 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/2409.03845 |
| 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/2409.03845 |
| primary_location.id | pmh:oai:arXiv.org:2409.03845 |
| 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/2409.03845 |
| 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/2409.03845 |
| publication_date | 2024-09-05 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 15, 29, 33, 47 |
| abstract_inverted_index.We | 91 |
| abstract_inverted_index.an | 59, 65, 106 |
| abstract_inverted_index.as | 84 |
| abstract_inverted_index.by | 46, 64 |
| abstract_inverted_index.in | 24, 87, 105 |
| abstract_inverted_index.is | 43, 71 |
| abstract_inverted_index.of | 32, 39, 81 |
| abstract_inverted_index.on | 111 |
| abstract_inverted_index.to | 8, 19, 73, 135 |
| abstract_inverted_index.Our | 12 |
| abstract_inverted_index.The | 37 |
| abstract_inverted_index.and | 115, 132 |
| abstract_inverted_index.can | 133 |
| abstract_inverted_index.new | 136 |
| abstract_inverted_index.our | 122 |
| abstract_inverted_index.the | 25, 54, 88, 93, 125 |
| abstract_inverted_index.This | 0, 69 |
| abstract_inverted_index.data | 22 |
| abstract_inverted_index.deep | 4 |
| abstract_inverted_index.each | 21 |
| abstract_inverted_index.from | 58, 77 |
| abstract_inverted_index.that | 121 |
| abstract_inverted_index.time | 26 |
| abstract_inverted_index.with | 53, 99, 124 |
| abstract_inverted_index.Carlo | 103 |
| abstract_inverted_index.Monte | 102 |
| abstract_inverted_index.chain | 101 |
| abstract_inverted_index.drawn | 57 |
| abstract_inverted_index.model | 18, 67, 94, 123 |
| abstract_inverted_index.novel | 3 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.point | 23 |
| abstract_inverted_index.prior | 61, 128 |
| abstract_inverted_index.state | 35, 56, 117 |
| abstract_inverted_index.these | 40 |
| abstract_inverted_index.train | 92 |
| abstract_inverted_index.using | 95 |
| abstract_inverted_index.(EBM). | 68 |
| abstract_inverted_index.(MCMC) | 104 |
| abstract_inverted_index.(ODE), | 52 |
| abstract_inverted_index.Markov | 100 |
| abstract_inverted_index.latent | 34, 41, 89 |
| abstract_inverted_index.models | 6 |
| abstract_inverted_index.neural | 16, 48 |
| abstract_inverted_index.series | 27 |
| abstract_inverted_index.space. | 90 |
| abstract_inverted_index.states | 42, 76 |
| abstract_inverted_index.static | 79 |
| abstract_inverted_index.videos | 114 |
| abstract_inverted_index.defined | 45 |
| abstract_inverted_index.dynamic | 75, 137 |
| abstract_inverted_index.employs | 14 |
| abstract_inverted_index.factors | 80 |
| abstract_inverted_index.initial | 55 |
| abstract_inverted_index.manner. | 108 |
| abstract_inverted_index.maximum | 96 |
| abstract_inverted_index.results | 110 |
| abstract_inverted_index.through | 28 |
| abstract_inverted_index.vector. | 36 |
| abstract_inverted_index.(MuJoCo) | 119 |
| abstract_inverted_index.approach | 13 |
| abstract_inverted_index.designed | 7 |
| abstract_inverted_index.emission | 17 |
| abstract_inverted_index.enabling | 139 |
| abstract_inverted_index.equation | 51 |
| abstract_inverted_index.existing | 130 |
| abstract_inverted_index.extended | 72 |
| abstract_inverted_index.generate | 20 |
| abstract_inverted_index.ordinary | 49 |
| abstract_inverted_index.systems, | 113 |
| abstract_inverted_index.dynamical | 5 |
| abstract_inverted_index.evolution | 38 |
| abstract_inverted_index.framework | 70 |
| abstract_inverted_index.learnable | 126 |
| abstract_inverted_index.represent | 9 |
| abstract_inverted_index.sequences | 118 |
| abstract_inverted_index.variables | 86 |
| abstract_inverted_index.end-to-end | 107 |
| abstract_inverted_index.estimation | 98 |
| abstract_inverted_index.generalize | 134 |
| abstract_inverted_index.implicitly | 44 |
| abstract_inverted_index.introduces | 2 |
| abstract_inverted_index.likelihood | 97 |
| abstract_inverted_index.non-linear | 30 |
| abstract_inverted_index.real-world | 116 |
| abstract_inverted_index.sequences. | 11 |
| abstract_inverted_index.underlying | 78 |
| abstract_inverted_index.variation, | 82 |
| abstract_inverted_index.demonstrate | 120 |
| abstract_inverted_index.disentangle | 74 |
| abstract_inverted_index.informative | 60 |
| abstract_inverted_index.oscillating | 112 |
| abstract_inverted_index.outperforms | 129 |
| abstract_inverted_index.represented | 83 |
| abstract_inverted_index.Energy-based | 66 |
| abstract_inverted_index.Experimental | 109 |
| abstract_inverted_index.differential | 50 |
| abstract_inverted_index.distribution | 62 |
| abstract_inverted_index.energy-based | 127 |
| abstract_inverted_index.long-horizon | 140 |
| abstract_inverted_index.predictions. | 141 |
| abstract_inverted_index.counterparts, | 131 |
| abstract_inverted_index.parameterized | 63 |
| abstract_inverted_index.time-invariant | 85 |
| abstract_inverted_index.transformation | 31 |
| abstract_inverted_index.continuous-time | 10 |
| abstract_inverted_index.parameterization, | 138 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |