Minimax Linear Regression under the Quantile Risk Article Swipe
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2406.12145
We study the problem of designing minimax procedures in linear regression under the quantile risk. We start by considering the realizable setting with independent Gaussian noise, where for any given noise level and distribution of inputs, we obtain the exact minimax quantile risk for a rich family of error functions and establish the minimaxity of OLS. This improves on the known lower bounds for the special case of square error, and provides us with a lower bound on the minimax quantile risk over larger sets of distributions. Under the square error and a fourth moment assumption on the distribution of inputs, we show that this lower bound is tight over a larger class of problems. Specifically, we prove a matching upper bound on the worst-case quantile risk of a variant of the recently proposed min-max regression procedure, thereby establishing its minimaxity, up to absolute constants. We illustrate the usefulness of our approach by extending this result to all $p$-th power error functions for $p \in (2, \infty)$. Along the way, we develop a generic analogue to the classical Bayesian method for lower bounding the minimax risk when working with the quantile risk, as well as a tight characterization of the quantiles of the smallest eigenvalue of the sample covariance matrix.
Related Topics
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2406.12145
- https://arxiv.org/pdf/2406.12145
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4399836889
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4399836889Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2406.12145Digital Object Identifier
- Title
-
Minimax Linear Regression under the Quantile RiskWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-06-17Full publication date if available
- Authors
-
Ayoub El Hanchi, Chris J. Maddison, Murat A. ErdogduList of authors in order
- Landing page
-
https://arxiv.org/abs/2406.12145Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2406.12145Direct 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/2406.12145Direct OA link when available
- Concepts
-
Minimax, Quantile regression, Linear regression, Econometrics, Quantile, Mathematics, Statistics, Computer science, Mathematical optimizationTop 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/W4399836889 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2406.12145 |
| ids.doi | https://doi.org/10.48550/arxiv.2406.12145 |
| ids.openalex | https://openalex.org/W4399836889 |
| fwci | |
| type | preprint |
| title | Minimax Linear Regression under the Quantile Risk |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11871 |
| topics[0].field.id | https://openalex.org/fields/26 |
| topics[0].field.display_name | Mathematics |
| topics[0].score | 0.6065000295639038 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2613 |
| topics[0].subfield.display_name | Statistics and Probability |
| topics[0].display_name | Advanced Statistical Methods and Models |
| topics[1].id | https://openalex.org/T10136 |
| topics[1].field.id | https://openalex.org/fields/26 |
| topics[1].field.display_name | Mathematics |
| topics[1].score | 0.5910999774932861 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2613 |
| topics[1].subfield.display_name | Statistics and Probability |
| topics[1].display_name | Statistical Methods and Inference |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C149728462 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8171842694282532 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q751319 |
| concepts[0].display_name | Minimax |
| concepts[1].id | https://openalex.org/C63817138 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6160156726837158 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q3455889 |
| concepts[1].display_name | Quantile regression |
| concepts[2].id | https://openalex.org/C48921125 |
| concepts[2].level | 2 |
| concepts[2].score | 0.532621443271637 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q10861030 |
| concepts[2].display_name | Linear regression |
| concepts[3].id | https://openalex.org/C149782125 |
| concepts[3].level | 1 |
| concepts[3].score | 0.518464982509613 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q160039 |
| concepts[3].display_name | Econometrics |
| concepts[4].id | https://openalex.org/C118671147 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5033802390098572 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q578714 |
| concepts[4].display_name | Quantile |
| concepts[5].id | https://openalex.org/C33923547 |
| concepts[5].level | 0 |
| concepts[5].score | 0.4283606708049774 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[5].display_name | Mathematics |
| concepts[6].id | https://openalex.org/C105795698 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3997443616390228 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[6].display_name | Statistics |
| concepts[7].id | https://openalex.org/C41008148 |
| concepts[7].level | 0 |
| concepts[7].score | 0.3214138150215149 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[7].display_name | Computer science |
| concepts[8].id | https://openalex.org/C126255220 |
| concepts[8].level | 1 |
| concepts[8].score | 0.22846096754074097 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q141495 |
| concepts[8].display_name | Mathematical optimization |
| keywords[0].id | https://openalex.org/keywords/minimax |
| keywords[0].score | 0.8171842694282532 |
| keywords[0].display_name | Minimax |
| keywords[1].id | https://openalex.org/keywords/quantile-regression |
| keywords[1].score | 0.6160156726837158 |
| keywords[1].display_name | Quantile regression |
| keywords[2].id | https://openalex.org/keywords/linear-regression |
| keywords[2].score | 0.532621443271637 |
| keywords[2].display_name | Linear regression |
| keywords[3].id | https://openalex.org/keywords/econometrics |
| keywords[3].score | 0.518464982509613 |
| keywords[3].display_name | Econometrics |
| keywords[4].id | https://openalex.org/keywords/quantile |
| keywords[4].score | 0.5033802390098572 |
| keywords[4].display_name | Quantile |
| keywords[5].id | https://openalex.org/keywords/mathematics |
| keywords[5].score | 0.4283606708049774 |
| keywords[5].display_name | Mathematics |
| keywords[6].id | https://openalex.org/keywords/statistics |
| keywords[6].score | 0.3997443616390228 |
| keywords[6].display_name | Statistics |
| keywords[7].id | https://openalex.org/keywords/computer-science |
| keywords[7].score | 0.3214138150215149 |
| keywords[7].display_name | Computer science |
| keywords[8].id | https://openalex.org/keywords/mathematical-optimization |
| keywords[8].score | 0.22846096754074097 |
| keywords[8].display_name | Mathematical optimization |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2406.12145 |
| 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/2406.12145 |
| 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/2406.12145 |
| locations[1].id | doi:10.48550/arxiv.2406.12145 |
| 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.2406.12145 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5079366629 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Ayoub El Hanchi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Hanchi, Ayoub El |
| authorships[0].is_corresponding | False |
| 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 | Maddison, Chris J. |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5022491830 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-4271-8921 |
| authorships[2].author.display_name | Murat A. Erdogdu |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Erdogdu, Murat A. |
| 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/2406.12145 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Minimax Linear Regression under the Quantile Risk |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11871 |
| primary_topic.field.id | https://openalex.org/fields/26 |
| primary_topic.field.display_name | Mathematics |
| primary_topic.score | 0.6065000295639038 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2613 |
| primary_topic.subfield.display_name | Statistics and Probability |
| primary_topic.display_name | Advanced Statistical Methods and Models |
| related_works | https://openalex.org/W4206511378, https://openalex.org/W4206618949, https://openalex.org/W2526321210, https://openalex.org/W3205863630, https://openalex.org/W4318833145, https://openalex.org/W2364275385, https://openalex.org/W4388704167, https://openalex.org/W2007977664, https://openalex.org/W4376874882, https://openalex.org/W2224749288 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2406.12145 |
| 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/2406.12145 |
| 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/2406.12145 |
| primary_location.id | pmh:oai:arXiv.org:2406.12145 |
| 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/2406.12145 |
| 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/2406.12145 |
| publication_date | 2024-06-17 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 44, 74, 92, 110, 118, 128, 172, 195 |
| abstract_inverted_index.$p | 163 |
| abstract_inverted_index.We | 0, 15, 145 |
| abstract_inverted_index.as | 192, 194 |
| abstract_inverted_index.by | 17, 152 |
| abstract_inverted_index.in | 8 |
| abstract_inverted_index.is | 107 |
| abstract_inverted_index.of | 4, 34, 47, 54, 67, 85, 99, 113, 127, 130, 149, 198, 201, 205 |
| abstract_inverted_index.on | 58, 77, 96, 122 |
| abstract_inverted_index.to | 142, 156, 175 |
| abstract_inverted_index.up | 141 |
| abstract_inverted_index.us | 72 |
| abstract_inverted_index.we | 36, 101, 116, 170 |
| abstract_inverted_index.(2, | 165 |
| abstract_inverted_index.\in | 164 |
| abstract_inverted_index.all | 157 |
| abstract_inverted_index.and | 32, 50, 70, 91 |
| abstract_inverted_index.any | 28 |
| abstract_inverted_index.for | 27, 43, 63, 162, 180 |
| abstract_inverted_index.its | 139 |
| abstract_inverted_index.our | 150 |
| abstract_inverted_index.the | 2, 12, 19, 38, 52, 59, 64, 78, 88, 97, 123, 131, 147, 168, 176, 183, 189, 199, 202, 206 |
| abstract_inverted_index.OLS. | 55 |
| abstract_inverted_index.This | 56 |
| abstract_inverted_index.case | 66 |
| abstract_inverted_index.over | 82, 109 |
| abstract_inverted_index.rich | 45 |
| abstract_inverted_index.risk | 42, 81, 126, 185 |
| abstract_inverted_index.sets | 84 |
| abstract_inverted_index.show | 102 |
| abstract_inverted_index.that | 103 |
| abstract_inverted_index.this | 104, 154 |
| abstract_inverted_index.way, | 169 |
| abstract_inverted_index.well | 193 |
| abstract_inverted_index.when | 186 |
| abstract_inverted_index.with | 22, 73, 188 |
| abstract_inverted_index.Along | 167 |
| abstract_inverted_index.Under | 87 |
| abstract_inverted_index.bound | 76, 106, 121 |
| abstract_inverted_index.class | 112 |
| abstract_inverted_index.error | 48, 90, 160 |
| abstract_inverted_index.exact | 39 |
| abstract_inverted_index.given | 29 |
| abstract_inverted_index.known | 60 |
| abstract_inverted_index.level | 31 |
| abstract_inverted_index.lower | 61, 75, 105, 181 |
| abstract_inverted_index.noise | 30 |
| abstract_inverted_index.power | 159 |
| abstract_inverted_index.prove | 117 |
| abstract_inverted_index.risk, | 191 |
| abstract_inverted_index.risk. | 14 |
| abstract_inverted_index.start | 16 |
| abstract_inverted_index.study | 1 |
| abstract_inverted_index.tight | 108, 196 |
| abstract_inverted_index.under | 11 |
| abstract_inverted_index.upper | 120 |
| abstract_inverted_index.where | 26 |
| abstract_inverted_index.$p$-th | 158 |
| abstract_inverted_index.bounds | 62 |
| abstract_inverted_index.error, | 69 |
| abstract_inverted_index.family | 46 |
| abstract_inverted_index.fourth | 93 |
| abstract_inverted_index.larger | 83, 111 |
| abstract_inverted_index.linear | 9 |
| abstract_inverted_index.method | 179 |
| abstract_inverted_index.moment | 94 |
| abstract_inverted_index.noise, | 25 |
| abstract_inverted_index.obtain | 37 |
| abstract_inverted_index.result | 155 |
| abstract_inverted_index.sample | 207 |
| abstract_inverted_index.square | 68, 89 |
| abstract_inverted_index.develop | 171 |
| abstract_inverted_index.generic | 173 |
| abstract_inverted_index.inputs, | 35, 100 |
| abstract_inverted_index.matrix. | 209 |
| abstract_inverted_index.min-max | 134 |
| abstract_inverted_index.minimax | 6, 40, 79, 184 |
| abstract_inverted_index.problem | 3 |
| abstract_inverted_index.setting | 21 |
| abstract_inverted_index.special | 65 |
| abstract_inverted_index.thereby | 137 |
| abstract_inverted_index.variant | 129 |
| abstract_inverted_index.working | 187 |
| abstract_inverted_index.Bayesian | 178 |
| abstract_inverted_index.Gaussian | 24 |
| abstract_inverted_index.absolute | 143 |
| abstract_inverted_index.analogue | 174 |
| abstract_inverted_index.approach | 151 |
| abstract_inverted_index.bounding | 182 |
| abstract_inverted_index.improves | 57 |
| abstract_inverted_index.matching | 119 |
| abstract_inverted_index.proposed | 133 |
| abstract_inverted_index.provides | 71 |
| abstract_inverted_index.quantile | 13, 41, 80, 125, 190 |
| abstract_inverted_index.recently | 132 |
| abstract_inverted_index.smallest | 203 |
| abstract_inverted_index.\infty)$. | 166 |
| abstract_inverted_index.classical | 177 |
| abstract_inverted_index.designing | 5 |
| abstract_inverted_index.establish | 51 |
| abstract_inverted_index.extending | 153 |
| abstract_inverted_index.functions | 49, 161 |
| abstract_inverted_index.problems. | 114 |
| abstract_inverted_index.quantiles | 200 |
| abstract_inverted_index.assumption | 95 |
| abstract_inverted_index.constants. | 144 |
| abstract_inverted_index.covariance | 208 |
| abstract_inverted_index.eigenvalue | 204 |
| abstract_inverted_index.illustrate | 146 |
| abstract_inverted_index.minimaxity | 53 |
| abstract_inverted_index.procedure, | 136 |
| abstract_inverted_index.procedures | 7 |
| abstract_inverted_index.realizable | 20 |
| abstract_inverted_index.regression | 10, 135 |
| abstract_inverted_index.usefulness | 148 |
| abstract_inverted_index.worst-case | 124 |
| abstract_inverted_index.considering | 18 |
| abstract_inverted_index.independent | 23 |
| abstract_inverted_index.minimaxity, | 140 |
| abstract_inverted_index.distribution | 33, 98 |
| abstract_inverted_index.establishing | 138 |
| abstract_inverted_index.Specifically, | 115 |
| abstract_inverted_index.distributions. | 86 |
| abstract_inverted_index.characterization | 197 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile |