Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts Article Swipe
Wouter Kool
,
Chris J. Maddison
,
Andriy Mnih
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.11817
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2109.11817
Training large-scale mixture of experts models efficiently on modern hardware requires assigning datapoints in a batch to different experts, each with a limited capacity. Recently proposed assignment procedures lack a probabilistic interpretation and use biased estimators for training. As an alternative, we propose two unbiased estimators based on principled stochastic assignment procedures: one that skips datapoints which exceed expert capacity, and one that samples perfectly balanced assignments using an extension of the Gumbel-Matching distribution [29]. Both estimators are unbiased, as they correct for the used sampling procedure. On a toy experiment, we find the `skip'-estimator is more effective than the balanced sampling one, and both are more robust in solving the task than biased alternatives.
Related Topics
Concepts
Estimator
Computer science
Gumbel distribution
Matching (statistics)
Sampling (signal processing)
Task (project management)
Probabilistic logic
Scale (ratio)
Artificial intelligence
Statistics
Mathematics
Extreme value theory
Engineering
Filter (signal processing)
Computer vision
Physics
Systems engineering
Quantum mechanics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2109.11817
- https://arxiv.org/pdf/2109.11817
- OA Status
- green
- References
- 38
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3202209116
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3202209116Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2109.11817Digital Object Identifier
- Title
-
Unbiased Gradient Estimation with Balanced Assignments for Mixtures of ExpertsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-09-24Full publication date if available
- Authors
-
Wouter Kool, Chris J. Maddison, Andriy MnihList of authors in order
- Landing page
-
https://arxiv.org/abs/2109.11817Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2109.11817Direct 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/2109.11817Direct OA link when available
- Concepts
-
Estimator, Computer science, Gumbel distribution, Matching (statistics), Sampling (signal processing), Task (project management), Probabilistic logic, Scale (ratio), Artificial intelligence, Statistics, Mathematics, Extreme value theory, Engineering, Filter (signal processing), Computer vision, Physics, Systems engineering, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
38Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3202209116 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2109.11817 |
| ids.doi | https://doi.org/10.48550/arxiv.2109.11817 |
| ids.mag | 3202209116 |
| ids.openalex | https://openalex.org/W3202209116 |
| fwci | |
| type | preprint |
| title | Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12072 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9998999834060669 |
| 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 | Machine Learning and Algorithms |
| topics[1].id | https://openalex.org/T12101 |
| topics[1].field.id | https://openalex.org/fields/18 |
| topics[1].field.display_name | Decision Sciences |
| topics[1].score | 0.9993000030517578 |
| 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 | Advanced Bandit Algorithms Research |
| topics[2].id | https://openalex.org/T12535 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9990000128746033 |
| 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 | Machine Learning and Data Classification |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C185429906 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7821856737136841 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q1130160 |
| concepts[0].display_name | Estimator |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.6659078598022461 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C137610916 |
| concepts[2].level | 3 |
| concepts[2].score | 0.6071339845657349 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q1096862 |
| concepts[2].display_name | Gumbel distribution |
| concepts[3].id | https://openalex.org/C165064840 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6031554937362671 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1321061 |
| concepts[3].display_name | Matching (statistics) |
| concepts[4].id | https://openalex.org/C140779682 |
| concepts[4].level | 3 |
| concepts[4].score | 0.5739946365356445 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q210868 |
| concepts[4].display_name | Sampling (signal processing) |
| concepts[5].id | https://openalex.org/C2780451532 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5570538640022278 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q759676 |
| concepts[5].display_name | Task (project management) |
| concepts[6].id | https://openalex.org/C49937458 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4777780771255493 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2599292 |
| concepts[6].display_name | Probabilistic logic |
| concepts[7].id | https://openalex.org/C2778755073 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4184606373310089 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q10858537 |
| concepts[7].display_name | Scale (ratio) |
| concepts[8].id | https://openalex.org/C154945302 |
| concepts[8].level | 1 |
| concepts[8].score | 0.31449776887893677 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[8].display_name | Artificial intelligence |
| concepts[9].id | https://openalex.org/C105795698 |
| concepts[9].level | 1 |
| concepts[9].score | 0.2518410086631775 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[9].display_name | Statistics |
| concepts[10].id | https://openalex.org/C33923547 |
| concepts[10].level | 0 |
| concepts[10].score | 0.2169513702392578 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[10].display_name | Mathematics |
| concepts[11].id | https://openalex.org/C147581598 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0755334198474884 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q729429 |
| concepts[11].display_name | Extreme value theory |
| concepts[12].id | https://openalex.org/C127413603 |
| concepts[12].level | 0 |
| concepts[12].score | 0.07278496026992798 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[12].display_name | Engineering |
| 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/C31972630 |
| concepts[14].level | 1 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q844240 |
| concepts[14].display_name | Computer vision |
| concepts[15].id | https://openalex.org/C121332964 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[15].display_name | Physics |
| concepts[16].id | https://openalex.org/C201995342 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q682496 |
| concepts[16].display_name | Systems engineering |
| concepts[17].id | https://openalex.org/C62520636 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[17].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/estimator |
| keywords[0].score | 0.7821856737136841 |
| keywords[0].display_name | Estimator |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.6659078598022461 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/gumbel-distribution |
| keywords[2].score | 0.6071339845657349 |
| keywords[2].display_name | Gumbel distribution |
| keywords[3].id | https://openalex.org/keywords/matching |
| keywords[3].score | 0.6031554937362671 |
| keywords[3].display_name | Matching (statistics) |
| keywords[4].id | https://openalex.org/keywords/sampling |
| keywords[4].score | 0.5739946365356445 |
| keywords[4].display_name | Sampling (signal processing) |
| keywords[5].id | https://openalex.org/keywords/task |
| keywords[5].score | 0.5570538640022278 |
| keywords[5].display_name | Task (project management) |
| keywords[6].id | https://openalex.org/keywords/probabilistic-logic |
| keywords[6].score | 0.4777780771255493 |
| keywords[6].display_name | Probabilistic logic |
| keywords[7].id | https://openalex.org/keywords/scale |
| keywords[7].score | 0.4184606373310089 |
| keywords[7].display_name | Scale (ratio) |
| keywords[8].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[8].score | 0.31449776887893677 |
| keywords[8].display_name | Artificial intelligence |
| keywords[9].id | https://openalex.org/keywords/statistics |
| keywords[9].score | 0.2518410086631775 |
| keywords[9].display_name | Statistics |
| keywords[10].id | https://openalex.org/keywords/mathematics |
| keywords[10].score | 0.2169513702392578 |
| keywords[10].display_name | Mathematics |
| keywords[11].id | https://openalex.org/keywords/extreme-value-theory |
| keywords[11].score | 0.0755334198474884 |
| keywords[11].display_name | Extreme value theory |
| keywords[12].id | https://openalex.org/keywords/engineering |
| keywords[12].score | 0.07278496026992798 |
| keywords[12].display_name | Engineering |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2109.11817 |
| 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/2109.11817 |
| 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/2109.11817 |
| locations[1].id | doi:10.48550/arxiv.2109.11817 |
| 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.2109.11817 |
| locations[2].id | mag:3202209116 |
| locations[2].is_oa | False |
| locations[2].source | |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | |
| locations[2].raw_type | |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5103284134 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1837-1454 |
| authorships[0].author.display_name | Wouter Kool |
| authorships[0].countries | NL |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I887064364 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Amsterdam |
| authorships[0].institutions[0].id | https://openalex.org/I887064364 |
| authorships[0].institutions[0].ror | https://ror.org/04dkp9463 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I887064364 |
| authorships[0].institutions[0].country_code | NL |
| authorships[0].institutions[0].display_name | University of Amsterdam |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Wouter Kool |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Amsterdam |
| authorships[1].author.id | https://openalex.org/A5054711904 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Chris J. Maddison |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Chris J. Maddison |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5079370148 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Andriy Mnih |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Andriy Mnih |
| 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/2109.11817 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12072 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9998999834060669 |
| 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 | Machine Learning and Algorithms |
| related_works | https://openalex.org/W2963306319, https://openalex.org/W2047948925, https://openalex.org/W1977245551, https://openalex.org/W2951964807, https://openalex.org/W3015472540, https://openalex.org/W2938226775, https://openalex.org/W2527636447, https://openalex.org/W2339183758, https://openalex.org/W2009954908, https://openalex.org/W3124685736, https://openalex.org/W2786776292, https://openalex.org/W3211458970, https://openalex.org/W3158114995, https://openalex.org/W3188165865, https://openalex.org/W2625701074, https://openalex.org/W2221646058, https://openalex.org/W2222829407, https://openalex.org/W2318168738, https://openalex.org/W2417583646, https://openalex.org/W2146879621 |
| cited_by_count | 0 |
| locations_count | 3 |
| best_oa_location.id | pmh:oai:arXiv.org:2109.11817 |
| 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/2109.11817 |
| 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/2109.11817 |
| primary_location.id | pmh:oai:arXiv.org:2109.11817 |
| 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/2109.11817 |
| 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/2109.11817 |
| publication_date | 2021-09-24 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W2963619462, https://openalex.org/W2166541787, https://openalex.org/W1555168537, https://openalex.org/W10548402, https://openalex.org/W3170943566, https://openalex.org/W2119717200, https://openalex.org/W2922485096, https://openalex.org/W2169943664, https://openalex.org/W2179423374, https://openalex.org/W1990283121, https://openalex.org/W1593114658, https://openalex.org/W2963549470, https://openalex.org/W3166104088, https://openalex.org/W2162980292, https://openalex.org/W2046765929, https://openalex.org/W1665115054, https://openalex.org/W2942190342, https://openalex.org/W2891768589, https://openalex.org/W3122317902, https://openalex.org/W1550892302, https://openalex.org/W2007572995, https://openalex.org/W2222512263, https://openalex.org/W2118853346, https://openalex.org/W2079639858, https://openalex.org/W2964316651, https://openalex.org/W3173073671, https://openalex.org/W2003447360, https://openalex.org/W3170796112, https://openalex.org/W2158131535, https://openalex.org/W2121863487, https://openalex.org/W2161611531, https://openalex.org/W2964121744, https://openalex.org/W2970600147, https://openalex.org/W2332308268, https://openalex.org/W2242818861, https://openalex.org/W2325237720, https://openalex.org/W2069259012, https://openalex.org/W3119866685 |
| referenced_works_count | 38 |
| abstract_inverted_index.a | 14, 21, 29, 88 |
| abstract_inverted_index.As | 38 |
| abstract_inverted_index.On | 87 |
| abstract_inverted_index.an | 39, 68 |
| abstract_inverted_index.as | 79 |
| abstract_inverted_index.in | 13, 108 |
| abstract_inverted_index.is | 95 |
| abstract_inverted_index.of | 3, 70 |
| abstract_inverted_index.on | 7, 47 |
| abstract_inverted_index.to | 16 |
| abstract_inverted_index.we | 41, 91 |
| abstract_inverted_index.and | 32, 60, 103 |
| abstract_inverted_index.are | 77, 105 |
| abstract_inverted_index.for | 36, 82 |
| abstract_inverted_index.one | 52, 61 |
| abstract_inverted_index.the | 71, 83, 93, 99, 110 |
| abstract_inverted_index.toy | 89 |
| abstract_inverted_index.two | 43 |
| abstract_inverted_index.use | 33 |
| abstract_inverted_index.Both | 75 |
| abstract_inverted_index.both | 104 |
| abstract_inverted_index.each | 19 |
| abstract_inverted_index.find | 92 |
| abstract_inverted_index.lack | 28 |
| abstract_inverted_index.more | 96, 106 |
| abstract_inverted_index.one, | 102 |
| abstract_inverted_index.task | 111 |
| abstract_inverted_index.than | 98, 112 |
| abstract_inverted_index.that | 53, 62 |
| abstract_inverted_index.they | 80 |
| abstract_inverted_index.used | 84 |
| abstract_inverted_index.with | 20 |
| abstract_inverted_index.[29]. | 74 |
| abstract_inverted_index.based | 46 |
| abstract_inverted_index.batch | 15 |
| abstract_inverted_index.skips | 54 |
| abstract_inverted_index.using | 67 |
| abstract_inverted_index.which | 56 |
| abstract_inverted_index.biased | 34, 113 |
| abstract_inverted_index.exceed | 57 |
| abstract_inverted_index.expert | 58 |
| abstract_inverted_index.models | 5 |
| abstract_inverted_index.modern | 8 |
| abstract_inverted_index.robust | 107 |
| abstract_inverted_index.correct | 81 |
| abstract_inverted_index.experts | 4 |
| abstract_inverted_index.limited | 22 |
| abstract_inverted_index.mixture | 2 |
| abstract_inverted_index.propose | 42 |
| abstract_inverted_index.samples | 63 |
| abstract_inverted_index.solving | 109 |
| abstract_inverted_index.Recently | 24 |
| abstract_inverted_index.Training | 0 |
| abstract_inverted_index.balanced | 65, 100 |
| abstract_inverted_index.experts, | 18 |
| abstract_inverted_index.hardware | 9 |
| abstract_inverted_index.proposed | 25 |
| abstract_inverted_index.requires | 10 |
| abstract_inverted_index.sampling | 85, 101 |
| abstract_inverted_index.unbiased | 44 |
| abstract_inverted_index.assigning | 11 |
| abstract_inverted_index.capacity, | 59 |
| abstract_inverted_index.capacity. | 23 |
| abstract_inverted_index.different | 17 |
| abstract_inverted_index.effective | 97 |
| abstract_inverted_index.extension | 69 |
| abstract_inverted_index.perfectly | 64 |
| abstract_inverted_index.training. | 37 |
| abstract_inverted_index.unbiased, | 78 |
| abstract_inverted_index.assignment | 26, 50 |
| abstract_inverted_index.datapoints | 12, 55 |
| abstract_inverted_index.estimators | 35, 45, 76 |
| abstract_inverted_index.principled | 48 |
| abstract_inverted_index.procedure. | 86 |
| abstract_inverted_index.procedures | 27 |
| abstract_inverted_index.stochastic | 49 |
| abstract_inverted_index.assignments | 66 |
| abstract_inverted_index.efficiently | 6 |
| abstract_inverted_index.experiment, | 90 |
| abstract_inverted_index.large-scale | 1 |
| abstract_inverted_index.procedures: | 51 |
| abstract_inverted_index.alternative, | 40 |
| abstract_inverted_index.distribution | 73 |
| abstract_inverted_index.alternatives. | 114 |
| abstract_inverted_index.probabilistic | 30 |
| abstract_inverted_index.interpretation | 31 |
| abstract_inverted_index.Gumbel-Matching | 72 |
| abstract_inverted_index.`skip'-estimator | 94 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |