Gaussian Gated Linear Networks Article Swipe
David Budden
,
Adam Marblestone
,
Eren Sezener
,
Tor Lattimore
,
Greg Wayne
,
Joel Veness
·
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2006.05964
YOU?
·
· 2020
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2006.05964
We propose the Gaussian Gated Linear Network (G-GLN), an extension to the recently proposed GLN family of deep neural networks. Instead of using backpropagation to learn features, GLNs have a distributed and local credit assignment mechanism based on optimizing a convex objective. This gives rise to many desirable properties including universality, data-efficient online learning, trivial interpretability and robustness to catastrophic forgetting. We extend the GLN framework from classification to multiple regression and density modelling by generalizing geometric mixing to a product of Gaussian densities. The G-GLN achieves competitive or state-of-the-art performance on several univariate and multivariate regression benchmarks, and we demonstrate its applicability to practical tasks including online contextual bandits and density estimation via denoising.
Related Topics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2006.05964
- https://arxiv.org/pdf/2006.05964
- OA Status
- green
- Cited By
- 6
- References
- 44
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3034795257
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3034795257Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2006.05964Digital Object Identifier
- Title
-
Gaussian Gated Linear NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2020Year of publication
- Publication date
-
2020-06-10Full publication date if available
- Authors
-
David Budden, Adam Marblestone, Eren Sezener, Tor Lattimore, Greg Wayne, Joel VenessList of authors in order
- Landing page
-
https://arxiv.org/abs/2006.05964Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2006.05964Direct 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/2006.05964Direct OA link when available
- Concepts
-
Gaussian, Computer science, Mathematics, Physics, Quantum mechanicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
6Total citation count in OpenAlex
- Citations by year (recent)
-
2024: 2, 2023: 3, 2022: 1Per-year citation counts (last 5 years)
- References (count)
-
44Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3034795257 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2006.05964 |
| ids.doi | https://doi.org/10.48550/arxiv.2006.05964 |
| ids.mag | 3034795257 |
| ids.openalex | https://openalex.org/W3034795257 |
| fwci | |
| type | preprint |
| title | Gaussian Gated Linear Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12814 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9926000237464905 |
| 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 | Gaussian Processes and Bayesian Inference |
| 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 | 0.9896000027656555 |
| 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/T11303 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9799000024795532 |
| 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 | Bayesian Modeling and Causal Inference |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C163716315 |
| concepts[0].level | 2 |
| concepts[0].score | 0.5209066271781921 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q901177 |
| concepts[0].display_name | Gaussian |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.35423147678375244 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C33923547 |
| concepts[2].level | 0 |
| concepts[2].score | 0.3260117471218109 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[2].display_name | Mathematics |
| concepts[3].id | https://openalex.org/C121332964 |
| concepts[3].level | 0 |
| concepts[3].score | 0.23894190788269043 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[3].display_name | Physics |
| concepts[4].id | https://openalex.org/C62520636 |
| concepts[4].level | 1 |
| concepts[4].score | 0.06271958351135254 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[4].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/gaussian |
| keywords[0].score | 0.5209066271781921 |
| keywords[0].display_name | Gaussian |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.35423147678375244 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/mathematics |
| keywords[2].score | 0.3260117471218109 |
| keywords[2].display_name | Mathematics |
| keywords[3].id | https://openalex.org/keywords/physics |
| keywords[3].score | 0.23894190788269043 |
| keywords[3].display_name | Physics |
| keywords[4].id | https://openalex.org/keywords/quantum-mechanics |
| keywords[4].score | 0.06271958351135254 |
| keywords[4].display_name | Quantum mechanics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2006.05964 |
| 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/2006.05964 |
| 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/2006.05964 |
| locations[1].id | doi:10.48550/arxiv.2006.05964 |
| 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.2006.05964 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5003238807 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4372-8985 |
| authorships[0].author.display_name | David Budden |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[0].affiliations[0].raw_affiliation_string | Google,,,,, |
| authorships[0].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[0].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Google (United States) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | David Budden |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Google,,,,, |
| authorships[1].author.id | https://openalex.org/A5033557144 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9833-9931 |
| authorships[1].author.display_name | Adam Marblestone |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Adam Marblestone |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5088896420 |
| authorships[2].author.orcid | |
| authorships[2].author.display_name | Eren Sezener |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Eren Sezener |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5017031238 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Tor Lattimore |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Tor Lattimore |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5013028446 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Greg Wayne |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Greg Wayne |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5060709021 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Joel Veness |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Joel Veness |
| 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/2006.05964 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Gaussian Gated Linear Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12814 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9926000237464905 |
| 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 | Gaussian Processes and Bayesian Inference |
| related_works | https://openalex.org/W2748952813, https://openalex.org/W4391375266, https://openalex.org/W1979597421, https://openalex.org/W2007980826, https://openalex.org/W2061531152, https://openalex.org/W3002753104, https://openalex.org/W2077600819, https://openalex.org/W2142036596, https://openalex.org/W2072657027, https://openalex.org/W2600246793 |
| cited_by_count | 6 |
| counts_by_year[0].year | 2024 |
| counts_by_year[0].cited_by_count | 2 |
| counts_by_year[1].year | 2023 |
| counts_by_year[1].cited_by_count | 3 |
| counts_by_year[2].year | 2022 |
| counts_by_year[2].cited_by_count | 1 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2006.05964 |
| 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/2006.05964 |
| 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/2006.05964 |
| primary_location.id | pmh:oai:arXiv.org:2006.05964 |
| 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/2006.05964 |
| 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/2006.05964 |
| publication_date | 2020-06-10 |
| publication_year | 2020 |
| referenced_works | https://openalex.org/W2771657877, https://openalex.org/W1510444525, https://openalex.org/W2124914669, https://openalex.org/W2513180554, https://openalex.org/W2149764047, https://openalex.org/W2099231026, https://openalex.org/W3006992011, https://openalex.org/W830076066, https://openalex.org/W2012833704, https://openalex.org/W3174224867, https://openalex.org/W2963921132, https://openalex.org/W1506806321, https://openalex.org/W2963580001, https://openalex.org/W1719489212, https://openalex.org/W2946054758, https://openalex.org/W2969724595, https://openalex.org/W2089217417, https://openalex.org/W2949536823, https://openalex.org/W1505878979, https://openalex.org/W2995029131, https://openalex.org/W2964330179, https://openalex.org/W2990583358, https://openalex.org/W2168405694, https://openalex.org/W2296319761, https://openalex.org/W2108677974, https://openalex.org/W2148825261, https://openalex.org/W2946894912, https://openalex.org/W241901432, https://openalex.org/W2622604310, https://openalex.org/W2952502547, https://openalex.org/W2120340025, https://openalex.org/W2013035813, https://openalex.org/W2614634292, https://openalex.org/W2997570648, https://openalex.org/W2077052576, https://openalex.org/W2271840356, https://openalex.org/W582134693, https://openalex.org/W3004619082, https://openalex.org/W2911586496, https://openalex.org/W2964319207, https://openalex.org/W2783494467, https://openalex.org/W2129069237, https://openalex.org/W2157992637, https://openalex.org/W2971246930 |
| referenced_works_count | 44 |
| abstract_inverted_index.a | 29, 39, 79 |
| abstract_inverted_index.We | 0, 61 |
| abstract_inverted_index.an | 8 |
| abstract_inverted_index.by | 74 |
| abstract_inverted_index.of | 16, 21, 81 |
| abstract_inverted_index.on | 37, 91 |
| abstract_inverted_index.or | 88 |
| abstract_inverted_index.to | 10, 24, 45, 58, 68, 78, 103 |
| abstract_inverted_index.we | 99 |
| abstract_inverted_index.GLN | 14, 64 |
| abstract_inverted_index.The | 84 |
| abstract_inverted_index.and | 31, 56, 71, 94, 98, 110 |
| abstract_inverted_index.its | 101 |
| abstract_inverted_index.the | 2, 11, 63 |
| abstract_inverted_index.via | 113 |
| abstract_inverted_index.GLNs | 27 |
| abstract_inverted_index.This | 42 |
| abstract_inverted_index.deep | 17 |
| abstract_inverted_index.from | 66 |
| abstract_inverted_index.have | 28 |
| abstract_inverted_index.many | 46 |
| abstract_inverted_index.rise | 44 |
| abstract_inverted_index.G-GLN | 85 |
| abstract_inverted_index.Gated | 4 |
| abstract_inverted_index.based | 36 |
| abstract_inverted_index.gives | 43 |
| abstract_inverted_index.learn | 25 |
| abstract_inverted_index.local | 32 |
| abstract_inverted_index.tasks | 105 |
| abstract_inverted_index.using | 22 |
| abstract_inverted_index.Linear | 5 |
| abstract_inverted_index.convex | 40 |
| abstract_inverted_index.credit | 33 |
| abstract_inverted_index.extend | 62 |
| abstract_inverted_index.family | 15 |
| abstract_inverted_index.mixing | 77 |
| abstract_inverted_index.neural | 18 |
| abstract_inverted_index.online | 52, 107 |
| abstract_inverted_index.Instead | 20 |
| abstract_inverted_index.Network | 6 |
| abstract_inverted_index.bandits | 109 |
| abstract_inverted_index.density | 72, 111 |
| abstract_inverted_index.product | 80 |
| abstract_inverted_index.propose | 1 |
| abstract_inverted_index.several | 92 |
| abstract_inverted_index.trivial | 54 |
| abstract_inverted_index.(G-GLN), | 7 |
| abstract_inverted_index.Gaussian | 3, 82 |
| abstract_inverted_index.achieves | 86 |
| abstract_inverted_index.multiple | 69 |
| abstract_inverted_index.proposed | 13 |
| abstract_inverted_index.recently | 12 |
| abstract_inverted_index.desirable | 47 |
| abstract_inverted_index.extension | 9 |
| abstract_inverted_index.features, | 26 |
| abstract_inverted_index.framework | 65 |
| abstract_inverted_index.geometric | 76 |
| abstract_inverted_index.including | 49, 106 |
| abstract_inverted_index.learning, | 53 |
| abstract_inverted_index.mechanism | 35 |
| abstract_inverted_index.modelling | 73 |
| abstract_inverted_index.networks. | 19 |
| abstract_inverted_index.practical | 104 |
| abstract_inverted_index.assignment | 34 |
| abstract_inverted_index.contextual | 108 |
| abstract_inverted_index.denoising. | 114 |
| abstract_inverted_index.densities. | 83 |
| abstract_inverted_index.estimation | 112 |
| abstract_inverted_index.objective. | 41 |
| abstract_inverted_index.optimizing | 38 |
| abstract_inverted_index.properties | 48 |
| abstract_inverted_index.regression | 70, 96 |
| abstract_inverted_index.robustness | 57 |
| abstract_inverted_index.univariate | 93 |
| abstract_inverted_index.benchmarks, | 97 |
| abstract_inverted_index.competitive | 87 |
| abstract_inverted_index.demonstrate | 100 |
| abstract_inverted_index.distributed | 30 |
| abstract_inverted_index.forgetting. | 60 |
| abstract_inverted_index.performance | 90 |
| abstract_inverted_index.catastrophic | 59 |
| abstract_inverted_index.generalizing | 75 |
| abstract_inverted_index.multivariate | 95 |
| abstract_inverted_index.applicability | 102 |
| abstract_inverted_index.universality, | 50 |
| abstract_inverted_index.classification | 67 |
| abstract_inverted_index.data-efficient | 51 |
| abstract_inverted_index.backpropagation | 23 |
| abstract_inverted_index.interpretability | 55 |
| abstract_inverted_index.state-of-the-art | 89 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |