Sliced Wasserstein with Random-Path Projecting Directions Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2401.15889
Slicing distribution selection has been used as an effective technique to improve the performance of parameter estimators based on minimizing sliced Wasserstein distance in applications. Previous works either utilize expensive optimization to select the slicing distribution or use slicing distributions that require expensive sampling methods. In this work, we propose an optimization-free slicing distribution that provides a fast sampling for the Monte Carlo estimation of expectation. In particular, we introduce the random-path projecting direction (RPD) which is constructed by leveraging the normalized difference between two random vectors following the two input measures. From the RPD, we derive the random-path slicing distribution (RPSD) and two variants of sliced Wasserstein, i.e., the Random-Path Projection Sliced Wasserstein (RPSW) and the Importance Weighted Random-Path Projection Sliced Wasserstein (IWRPSW). We then discuss the topological, statistical, and computational properties of RPSW and IWRPSW. Finally, we showcase the favorable performance of RPSW and IWRPSW in gradient flow and the training of denoising diffusion generative models on images.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2401.15889
- https://arxiv.org/pdf/2401.15889
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4391376518
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4391376518Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2401.15889Digital Object Identifier
- Title
-
Sliced Wasserstein with Random-Path Projecting DirectionsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-01-29Full publication date if available
- Authors
-
Minh‐Khai Nguyen, Shujian Zhang, Tam Le, Nhat HoList of authors in order
- Landing page
-
https://arxiv.org/abs/2401.15889Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2401.15889Direct 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/2401.15889Direct OA link when available
- Concepts
-
Path (computing), Mathematics, Computer science, Computer networkTop 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/W4391376518 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2401.15889 |
| ids.doi | https://doi.org/10.48550/arxiv.2401.15889 |
| ids.openalex | https://openalex.org/W4391376518 |
| fwci | |
| type | preprint |
| title | Sliced Wasserstein with Random-Path Projecting Directions |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12923 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9175999760627747 |
| 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 | Digital Image Processing Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C2777735758 |
| concepts[0].level | 2 |
| concepts[0].score | 0.5701417922973633 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q817765 |
| concepts[0].display_name | Path (computing) |
| concepts[1].id | https://openalex.org/C33923547 |
| concepts[1].level | 0 |
| concepts[1].score | 0.4720395803451538 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[1].display_name | Mathematics |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.3680325448513031 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C31258907 |
| concepts[3].level | 1 |
| concepts[3].score | 0.050159305334091187 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[3].display_name | Computer network |
| keywords[0].id | https://openalex.org/keywords/path |
| keywords[0].score | 0.5701417922973633 |
| keywords[0].display_name | Path (computing) |
| keywords[1].id | https://openalex.org/keywords/mathematics |
| keywords[1].score | 0.4720395803451538 |
| keywords[1].display_name | Mathematics |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.3680325448513031 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/computer-network |
| keywords[3].score | 0.050159305334091187 |
| keywords[3].display_name | Computer network |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2401.15889 |
| 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/2401.15889 |
| 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/2401.15889 |
| locations[1].id | doi:10.48550/arxiv.2401.15889 |
| 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.2401.15889 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5084111028 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1774-0817 |
| authorships[0].author.display_name | Minh‐Khai Nguyen |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Nguyen, Khai |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5056212977 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3216-722X |
| authorships[1].author.display_name | Shujian Zhang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhang, Shujian |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100583774 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Tam Le |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Le, Tam |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5112412955 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Nhat Ho |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Ho, Nhat |
| authorships[3].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/2401.15889 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Sliced Wasserstein with Random-Path Projecting Directions |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12923 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9175999760627747 |
| 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 | Digital Image Processing Techniques |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W1979597421, https://openalex.org/W2007980826, https://openalex.org/W4245490552, https://openalex.org/W4225152035, https://openalex.org/W2061531152, https://openalex.org/W3002753104, https://openalex.org/W2077600819, https://openalex.org/W1587224694, https://openalex.org/W2911598644 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2401.15889 |
| 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/2401.15889 |
| 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/2401.15889 |
| primary_location.id | pmh:oai:arXiv.org:2401.15889 |
| 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/2401.15889 |
| 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/2401.15889 |
| publication_date | 2024-01-29 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 56 |
| abstract_inverted_index.In | 45, 66 |
| abstract_inverted_index.We | 124 |
| abstract_inverted_index.an | 7, 50 |
| abstract_inverted_index.as | 6 |
| abstract_inverted_index.by | 78 |
| abstract_inverted_index.in | 23, 147 |
| abstract_inverted_index.is | 76 |
| abstract_inverted_index.of | 14, 64, 105, 133, 143, 153 |
| abstract_inverted_index.on | 18, 158 |
| abstract_inverted_index.or | 36 |
| abstract_inverted_index.to | 10, 31 |
| abstract_inverted_index.we | 48, 68, 95, 138 |
| abstract_inverted_index.and | 102, 115, 130, 135, 145, 150 |
| abstract_inverted_index.for | 59 |
| abstract_inverted_index.has | 3 |
| abstract_inverted_index.the | 12, 33, 60, 70, 80, 88, 93, 97, 109, 116, 127, 140, 151 |
| abstract_inverted_index.two | 84, 89, 103 |
| abstract_inverted_index.use | 37 |
| abstract_inverted_index.From | 92 |
| abstract_inverted_index.RPD, | 94 |
| abstract_inverted_index.RPSW | 134, 144 |
| abstract_inverted_index.been | 4 |
| abstract_inverted_index.fast | 57 |
| abstract_inverted_index.flow | 149 |
| abstract_inverted_index.that | 40, 54 |
| abstract_inverted_index.then | 125 |
| abstract_inverted_index.this | 46 |
| abstract_inverted_index.used | 5 |
| abstract_inverted_index.(RPD) | 74 |
| abstract_inverted_index.Carlo | 62 |
| abstract_inverted_index.Monte | 61 |
| abstract_inverted_index.based | 17 |
| abstract_inverted_index.i.e., | 108 |
| abstract_inverted_index.input | 90 |
| abstract_inverted_index.which | 75 |
| abstract_inverted_index.work, | 47 |
| abstract_inverted_index.works | 26 |
| abstract_inverted_index.(RPSD) | 101 |
| abstract_inverted_index.(RPSW) | 114 |
| abstract_inverted_index.IWRPSW | 146 |
| abstract_inverted_index.Sliced | 112, 121 |
| abstract_inverted_index.derive | 96 |
| abstract_inverted_index.either | 27 |
| abstract_inverted_index.models | 157 |
| abstract_inverted_index.random | 85 |
| abstract_inverted_index.select | 32 |
| abstract_inverted_index.sliced | 20, 106 |
| abstract_inverted_index.IWRPSW. | 136 |
| abstract_inverted_index.Slicing | 0 |
| abstract_inverted_index.between | 83 |
| abstract_inverted_index.discuss | 126 |
| abstract_inverted_index.images. | 159 |
| abstract_inverted_index.improve | 11 |
| abstract_inverted_index.propose | 49 |
| abstract_inverted_index.require | 41 |
| abstract_inverted_index.slicing | 34, 38, 52, 99 |
| abstract_inverted_index.utilize | 28 |
| abstract_inverted_index.vectors | 86 |
| abstract_inverted_index.Finally, | 137 |
| abstract_inverted_index.Previous | 25 |
| abstract_inverted_index.Weighted | 118 |
| abstract_inverted_index.distance | 22 |
| abstract_inverted_index.gradient | 148 |
| abstract_inverted_index.methods. | 44 |
| abstract_inverted_index.provides | 55 |
| abstract_inverted_index.sampling | 43, 58 |
| abstract_inverted_index.showcase | 139 |
| abstract_inverted_index.training | 152 |
| abstract_inverted_index.variants | 104 |
| abstract_inverted_index.(IWRPSW). | 123 |
| abstract_inverted_index.denoising | 154 |
| abstract_inverted_index.diffusion | 155 |
| abstract_inverted_index.direction | 73 |
| abstract_inverted_index.effective | 8 |
| abstract_inverted_index.expensive | 29, 42 |
| abstract_inverted_index.favorable | 141 |
| abstract_inverted_index.following | 87 |
| abstract_inverted_index.introduce | 69 |
| abstract_inverted_index.measures. | 91 |
| abstract_inverted_index.parameter | 15 |
| abstract_inverted_index.selection | 2 |
| abstract_inverted_index.technique | 9 |
| abstract_inverted_index.Importance | 117 |
| abstract_inverted_index.Projection | 111, 120 |
| abstract_inverted_index.difference | 82 |
| abstract_inverted_index.estimation | 63 |
| abstract_inverted_index.estimators | 16 |
| abstract_inverted_index.generative | 156 |
| abstract_inverted_index.leveraging | 79 |
| abstract_inverted_index.minimizing | 19 |
| abstract_inverted_index.normalized | 81 |
| abstract_inverted_index.projecting | 72 |
| abstract_inverted_index.properties | 132 |
| abstract_inverted_index.Random-Path | 110, 119 |
| abstract_inverted_index.Wasserstein | 21, 113, 122 |
| abstract_inverted_index.constructed | 77 |
| abstract_inverted_index.particular, | 67 |
| abstract_inverted_index.performance | 13, 142 |
| abstract_inverted_index.random-path | 71, 98 |
| abstract_inverted_index.Wasserstein, | 107 |
| abstract_inverted_index.distribution | 1, 35, 53, 100 |
| abstract_inverted_index.expectation. | 65 |
| abstract_inverted_index.optimization | 30 |
| abstract_inverted_index.statistical, | 129 |
| abstract_inverted_index.topological, | 128 |
| abstract_inverted_index.applications. | 24 |
| abstract_inverted_index.computational | 131 |
| abstract_inverted_index.distributions | 39 |
| abstract_inverted_index.optimization-free | 51 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |