On the Limitations of Representing Functions on Sets
Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular, it has been conjectured that the dimension of this latent space may remain fixed as the cardinality of the sets under consideration increases...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
07.10.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular, it has been conjectured that the dimension of this latent space may remain fixed as the cardinality of the sets under consideration increases. However, we demonstrate that the analysis leading to this conjecture requires mappings which are highly discontinuous and argue that this is only of limited practical use. Motivated by this observation, we prove that an implementation of this model via continuous mappings (as provided by e.g. neural networks or Gaussian processes) actually imposes a constraint on the dimensionality of the latent space. Practical universal function representation for set inputs can only be achieved with a latent dimension at least the size of the maximum number of input elements. |
---|---|
AbstractList | Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular, it has been conjectured that the dimension of this latent space may remain fixed as the cardinality of the sets under consideration increases. However, we demonstrate that the analysis leading to this conjecture requires mappings which are highly discontinuous and argue that this is only of limited practical use. Motivated by this observation, we prove that an implementation of this model via continuous mappings (as provided by e.g. neural networks or Gaussian processes) actually imposes a constraint on the dimensionality of the latent space. Practical universal function representation for set inputs can only be achieved with a latent dimension at least the size of the maximum number of input elements. |
Author | Engelcke, Martin Osborne, Michael Posner, Ingmar Wagstaff, Edward Fuchs, Fabian B |
Author_xml | – sequence: 1 givenname: Edward surname: Wagstaff fullname: Wagstaff, Edward – sequence: 2 givenname: Fabian surname: Fuchs middlename: B fullname: Fuchs, Fabian B – sequence: 3 givenname: Martin surname: Engelcke fullname: Engelcke, Martin – sequence: 4 givenname: Ingmar surname: Posner fullname: Posner, Ingmar – sequence: 5 givenname: Michael surname: Osborne fullname: Osborne, Michael |
BookMark | eNqNys0KgkAUQOEhCrLyHS60Fpwf09aRtAiCci8S1xqpOzZ35v1r4QO0OovvrMScHOFMJEprmVVGqaVImYc8z9WuVEWhE2EuBOGJcLZvG7pgHTG4Hq44emSkYOkBdaT7JAQ3DLwRi757MaZT12JbH5vDKRu9-0Tk0A4uevpRq2Qpq72RWur_ri926TYs |
ContentType | Paper |
Copyright | 2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2019. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials AUTh Library subscriptions: ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content (ProQuest) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_21718941313 |
IEDL.DBID | 8FG |
IngestDate | Thu Oct 10 18:37:03 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_21718941313 |
OpenAccessLink | https://www.proquest.com/docview/2171894131?pq-origsite=%requestingapplication% |
PQID | 2171894131 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2171894131 |
PublicationCentury | 2000 |
PublicationDate | 20191007 |
PublicationDateYYYYMMDD | 2019-10-07 |
PublicationDate_xml | – month: 10 year: 2019 text: 20191007 day: 07 |
PublicationDecade | 2010 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2019 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.2344558 |
SecondaryResourceType | preprint |
Snippet | Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular,... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Energy management Gaussian process Neural networks Permutations Representations |
Title | On the Limitations of Representing Functions on Sets |
URI | https://www.proquest.com/docview/2171894131 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dS8MwED90RfDNT_yYI6CvwaVNk_ZJUFqHsDmmwt5G0l4fu7l2r_7tXmKn4MMew0FyhOT3u7vc5QDudKR0mBjFy7hIuAxxyK0hZ8UqjdKYOJWVq0YeT9ToQ77M43kXcGu6tMotJnqgLpeFi5Hfk-kskpQgVzysPrnrGuVeV7sWGvsQCPcTnqsUz59_Yywh6RG7tsf_YNZzR34EwdSscH0Me1ifwIFPuSyaU5CvNSPri_kSo5-4GVtWbOZTU9E3cGA5sU4nqdkbts0Z3ObZ-9OIb5dadIehWfypHp1Dj7x6vABGvG-1RBkpYaVAshMquhraaBsNwxLTS-jvmulqt_gaDonZU591pvvQa9cbvCH2bO3Ab9EAgsdsMp3RaPyVfQPvhXkZ |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NT8MwDLVgE4Ibn-JjQCS4RqxtmrQnDohSYBsIhrRblbTusRtr-f84IQOJw86REity_GznWQ_gWkVShYmWvIrLhIsQh9xoKlaMVCi0jlNR22nk8UTmH-JpFs98w631tMpVTHSBupqXtkd-Q6lzkKQUcoPbxSe3qlH2d9VLaGxCX0Qysn6eZA-_PZaQ7Iit7PG_MOuwI9uF_qte4HIPNrDZhy1HuSzbAxAvDaPsi7kRo5--GZvX7M1RU9EJOLCMUMevNOwdu_YQrrL76V3OV0cV3hna4s_06Ah6VNXjMTDCfaMEktmBEQFSnlDT01BamWgYVpiewGDdTqfrly9hO5-OR8XocfJ8BjuE8qljoKkB9LrlF54Tknbmwl3XNxBueTY |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=On+the+Limitations+of+Representing+Functions+on+Sets&rft.jtitle=arXiv.org&rft.au=Wagstaff%2C+Edward&rft.au=Fuchs%2C+Fabian+B&rft.au=Engelcke%2C+Martin&rft.au=Posner%2C+Ingmar&rft.date=2019-10-07&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |