Differentiable Distributionally Robust Optimization Layers Article Swipe
Xutao Ma
,
Chao Ning
,
Wenli Du
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.16571
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.16571
In recent years, there has been a growing research interest in decision-focused learning, which embeds optimization problems as a layer in learning pipelines and demonstrates a superior performance than the prediction-focused approach. However, for distributionally robust optimization (DRO), a popular paradigm for decision-making under uncertainty, it is still unknown how to embed it as a layer, i.e., how to differentiate decisions with respect to an ambiguity set. In this paper, we develop such differentiable DRO layers for generic mixed-integer DRO problems with parameterized second-order conic ambiguity sets and discuss its extension to Wasserstein ambiguity sets. To differentiate the mixed-integer decisions, we propose a novel dual-view methodology by handling continuous and discrete parts of decisions via different principles. Specifically, we construct a differentiable energy-based surrogate to implement the dual-view methodology and use importance sampling to estimate its gradient. We further prove that such a surrogate enjoys the asymptotic convergency under regularization. As an application of the proposed differentiable DRO layers, we develop a novel decision-focused learning pipeline for contextual distributionally robust decision-making tasks and compare it with the prediction-focused approach in experiments.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2406.16571
- https://arxiv.org/pdf/2406.16571
- OA Status
- green
- Cited By
- 1
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4400024381
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4400024381Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2406.16571Digital Object Identifier
- Title
-
Differentiable Distributionally Robust Optimization LayersWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-06-24Full publication date if available
- Authors
-
Xutao Ma, Chao Ning, Wenli DuList of authors in order
- Landing page
-
https://arxiv.org/abs/2406.16571Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2406.16571Direct 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/2406.16571Direct OA link when available
- Concepts
-
Differentiable function, Robust optimization, Mathematical optimization, Optimization problem, Computer science, Mathematical economics, Mathematics, Mathematical analysisTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
1Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 1Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4400024381 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2406.16571 |
| ids.doi | https://doi.org/10.48550/arxiv.2406.16571 |
| ids.openalex | https://openalex.org/W4400024381 |
| fwci | |
| type | preprint |
| title | Differentiable Distributionally Robust Optimization Layers |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11413 |
| topics[0].field.id | https://openalex.org/fields/18 |
| topics[0].field.display_name | Decision Sciences |
| topics[0].score | 0.4722999930381775 |
| topics[0].domain.id | https://openalex.org/domains/2 |
| topics[0].domain.display_name | Social Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1803 |
| topics[0].subfield.display_name | Management Science and Operations Research |
| topics[0].display_name | Risk and Portfolio Optimization |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C202615002 |
| concepts[0].level | 2 |
| concepts[0].score | 0.687440037727356 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q783507 |
| concepts[0].display_name | Differentiable function |
| concepts[1].id | https://openalex.org/C193254401 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6712767481803894 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q2160088 |
| concepts[1].display_name | Robust optimization |
| concepts[2].id | https://openalex.org/C126255220 |
| concepts[2].level | 1 |
| concepts[2].score | 0.5394805669784546 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[2].display_name | Mathematical optimization |
| concepts[3].id | https://openalex.org/C137836250 |
| concepts[3].level | 2 |
| concepts[3].score | 0.42583608627319336 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q984063 |
| concepts[3].display_name | Optimization problem |
| concepts[4].id | https://openalex.org/C41008148 |
| concepts[4].level | 0 |
| concepts[4].score | 0.40765416622161865 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[4].display_name | Computer science |
| concepts[5].id | https://openalex.org/C144237770 |
| concepts[5].level | 1 |
| concepts[5].score | 0.33424854278564453 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q747534 |
| concepts[5].display_name | Mathematical economics |
| concepts[6].id | https://openalex.org/C33923547 |
| concepts[6].level | 0 |
| concepts[6].score | 0.3062741160392761 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[6].display_name | Mathematics |
| concepts[7].id | https://openalex.org/C134306372 |
| concepts[7].level | 1 |
| concepts[7].score | 0.09488889575004578 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7754 |
| concepts[7].display_name | Mathematical analysis |
| keywords[0].id | https://openalex.org/keywords/differentiable-function |
| keywords[0].score | 0.687440037727356 |
| keywords[0].display_name | Differentiable function |
| keywords[1].id | https://openalex.org/keywords/robust-optimization |
| keywords[1].score | 0.6712767481803894 |
| keywords[1].display_name | Robust optimization |
| keywords[2].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[2].score | 0.5394805669784546 |
| keywords[2].display_name | Mathematical optimization |
| keywords[3].id | https://openalex.org/keywords/optimization-problem |
| keywords[3].score | 0.42583608627319336 |
| keywords[3].display_name | Optimization problem |
| keywords[4].id | https://openalex.org/keywords/computer-science |
| keywords[4].score | 0.40765416622161865 |
| keywords[4].display_name | Computer science |
| keywords[5].id | https://openalex.org/keywords/mathematical-economics |
| keywords[5].score | 0.33424854278564453 |
| keywords[5].display_name | Mathematical economics |
| keywords[6].id | https://openalex.org/keywords/mathematics |
| keywords[6].score | 0.3062741160392761 |
| keywords[6].display_name | Mathematics |
| keywords[7].id | https://openalex.org/keywords/mathematical-analysis |
| keywords[7].score | 0.09488889575004578 |
| keywords[7].display_name | Mathematical analysis |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2406.16571 |
| 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/2406.16571 |
| 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/2406.16571 |
| locations[1].id | doi:10.48550/arxiv.2406.16571 |
| 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.2406.16571 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102745520 |
| authorships[0].author.orcid | https://orcid.org/0009-0001-7876-8576 |
| authorships[0].author.display_name | Xutao Ma |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ma, Xutao |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101987935 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3064-9551 |
| authorships[1].author.display_name | Chao Ning |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Ning, Chao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5048267931 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-2676-6341 |
| authorships[2].author.display_name | Wenli Du |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Du, Wenli |
| authorships[2].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/2406.16571 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Differentiable Distributionally Robust Optimization Layers |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11413 |
| primary_topic.field.id | https://openalex.org/fields/18 |
| primary_topic.field.display_name | Decision Sciences |
| primary_topic.score | 0.4722999930381775 |
| primary_topic.domain.id | https://openalex.org/domains/2 |
| primary_topic.domain.display_name | Social Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1803 |
| primary_topic.subfield.display_name | Management Science and Operations Research |
| primary_topic.display_name | Risk and Portfolio Optimization |
| related_works | https://openalex.org/W3005017983, https://openalex.org/W2205708137, https://openalex.org/W3182145356, https://openalex.org/W3212504317, https://openalex.org/W3149055374, https://openalex.org/W2053131036, https://openalex.org/W2216231335, https://openalex.org/W1988872022, https://openalex.org/W3195104199, https://openalex.org/W2224558845 |
| cited_by_count | 1 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2406.16571 |
| 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/2406.16571 |
| 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/2406.16571 |
| primary_location.id | pmh:oai:arXiv.org:2406.16571 |
| 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/2406.16571 |
| 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/2406.16571 |
| publication_date | 2024-06-24 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 6, 18, 25, 38, 54, 102, 120, 142, 161 |
| abstract_inverted_index.As | 150 |
| abstract_inverted_index.In | 0, 67 |
| abstract_inverted_index.To | 95 |
| abstract_inverted_index.We | 137 |
| abstract_inverted_index.an | 64, 151 |
| abstract_inverted_index.as | 17, 53 |
| abstract_inverted_index.by | 106 |
| abstract_inverted_index.in | 10, 20, 179 |
| abstract_inverted_index.is | 46 |
| abstract_inverted_index.it | 45, 52, 174 |
| abstract_inverted_index.of | 112, 153 |
| abstract_inverted_index.to | 50, 58, 63, 91, 124, 133 |
| abstract_inverted_index.we | 70, 100, 118, 159 |
| abstract_inverted_index.DRO | 74, 79, 157 |
| abstract_inverted_index.and | 23, 87, 109, 129, 172 |
| abstract_inverted_index.for | 33, 41, 76, 166 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.how | 49, 57 |
| abstract_inverted_index.its | 89, 135 |
| abstract_inverted_index.the | 29, 97, 126, 145, 154, 176 |
| abstract_inverted_index.use | 130 |
| abstract_inverted_index.via | 114 |
| abstract_inverted_index.been | 5 |
| abstract_inverted_index.set. | 66 |
| abstract_inverted_index.sets | 86 |
| abstract_inverted_index.such | 72, 141 |
| abstract_inverted_index.than | 28 |
| abstract_inverted_index.that | 140 |
| abstract_inverted_index.this | 68 |
| abstract_inverted_index.with | 61, 81, 175 |
| abstract_inverted_index.conic | 84 |
| abstract_inverted_index.embed | 51 |
| abstract_inverted_index.i.e., | 56 |
| abstract_inverted_index.layer | 19 |
| abstract_inverted_index.novel | 103, 162 |
| abstract_inverted_index.parts | 111 |
| abstract_inverted_index.prove | 139 |
| abstract_inverted_index.sets. | 94 |
| abstract_inverted_index.still | 47 |
| abstract_inverted_index.tasks | 171 |
| abstract_inverted_index.there | 3 |
| abstract_inverted_index.under | 43, 148 |
| abstract_inverted_index.which | 13 |
| abstract_inverted_index.(DRO), | 37 |
| abstract_inverted_index.embeds | 14 |
| abstract_inverted_index.enjoys | 144 |
| abstract_inverted_index.layer, | 55 |
| abstract_inverted_index.layers | 75 |
| abstract_inverted_index.paper, | 69 |
| abstract_inverted_index.recent | 1 |
| abstract_inverted_index.robust | 35, 169 |
| abstract_inverted_index.years, | 2 |
| abstract_inverted_index.compare | 173 |
| abstract_inverted_index.develop | 71, 160 |
| abstract_inverted_index.discuss | 88 |
| abstract_inverted_index.further | 138 |
| abstract_inverted_index.generic | 77 |
| abstract_inverted_index.growing | 7 |
| abstract_inverted_index.layers, | 158 |
| abstract_inverted_index.popular | 39 |
| abstract_inverted_index.propose | 101 |
| abstract_inverted_index.respect | 62 |
| abstract_inverted_index.unknown | 48 |
| abstract_inverted_index.However, | 32 |
| abstract_inverted_index.approach | 178 |
| abstract_inverted_index.discrete | 110 |
| abstract_inverted_index.estimate | 134 |
| abstract_inverted_index.handling | 107 |
| abstract_inverted_index.interest | 9 |
| abstract_inverted_index.learning | 21, 164 |
| abstract_inverted_index.paradigm | 40 |
| abstract_inverted_index.pipeline | 165 |
| abstract_inverted_index.problems | 16, 80 |
| abstract_inverted_index.proposed | 155 |
| abstract_inverted_index.research | 8 |
| abstract_inverted_index.sampling | 132 |
| abstract_inverted_index.superior | 26 |
| abstract_inverted_index.ambiguity | 65, 85, 93 |
| abstract_inverted_index.approach. | 31 |
| abstract_inverted_index.construct | 119 |
| abstract_inverted_index.decisions | 60, 113 |
| abstract_inverted_index.different | 115 |
| abstract_inverted_index.dual-view | 104, 127 |
| abstract_inverted_index.extension | 90 |
| abstract_inverted_index.gradient. | 136 |
| abstract_inverted_index.implement | 125 |
| abstract_inverted_index.learning, | 12 |
| abstract_inverted_index.pipelines | 22 |
| abstract_inverted_index.surrogate | 123, 143 |
| abstract_inverted_index.asymptotic | 146 |
| abstract_inverted_index.contextual | 167 |
| abstract_inverted_index.continuous | 108 |
| abstract_inverted_index.decisions, | 99 |
| abstract_inverted_index.importance | 131 |
| abstract_inverted_index.Wasserstein | 92 |
| abstract_inverted_index.application | 152 |
| abstract_inverted_index.convergency | 147 |
| abstract_inverted_index.methodology | 105, 128 |
| abstract_inverted_index.performance | 27 |
| abstract_inverted_index.principles. | 116 |
| abstract_inverted_index.demonstrates | 24 |
| abstract_inverted_index.energy-based | 122 |
| abstract_inverted_index.experiments. | 180 |
| abstract_inverted_index.optimization | 15, 36 |
| abstract_inverted_index.second-order | 83 |
| abstract_inverted_index.uncertainty, | 44 |
| abstract_inverted_index.Specifically, | 117 |
| abstract_inverted_index.differentiate | 59, 96 |
| abstract_inverted_index.mixed-integer | 78, 98 |
| abstract_inverted_index.parameterized | 82 |
| abstract_inverted_index.differentiable | 73, 121, 156 |
| abstract_inverted_index.decision-making | 42, 170 |
| abstract_inverted_index.regularization. | 149 |
| abstract_inverted_index.decision-focused | 11, 163 |
| abstract_inverted_index.distributionally | 34, 168 |
| abstract_inverted_index.prediction-focused | 30, 177 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |