Private and polynomial time algorithms for learning Gaussians and beyond
We present a fairly general framework for reducing \((\varepsilon, \delta)\) differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and \((\varepsilon,\delta)\)-DP algorithm for learning (unrestricted) G...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
22.06.2022
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | We present a fairly general framework for reducing \((\varepsilon, \delta)\) differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and \((\varepsilon,\delta)\)-DP algorithm for learning (unrestricted) Gaussian distributions in \(\mathbb{R}^d\). The sample complexity of our approach for learning the Gaussian up to total variation distance \(\alpha\) is \(\widetilde{O}(d^2/\alpha^2 + d^2\sqrt{\ln(1/\delta)}/\alpha \varepsilon + d\ln(1/\delta) / \alpha \varepsilon)\) matching (up to logarithmic factors) the best known information-theoretic (non-efficient) sample complexity upper bound due to Aden-Ali, Ashtiani, and Kamath (ALT'21). In an independent work, Kamath, Mouzakis, Singhal, Steinke, and Ullman (arXiv:2111.04609) proved a similar result using a different approach and with \(O(d^{5/2})\) sample complexity dependence on \(d\). As another application of our framework, we provide the first polynomial time \((\varepsilon, \delta)\)-DP algorithm for robust learning of (unrestricted) Gaussians with sample complexity \(\widetilde{O}(d^{3.5})\). In another independent work, Kothari, Manurangsi, and Velingker (arXiv:2112.03548) also provided a polynomial time \((\varepsilon, \delta)\)-DP algorithm for robust learning of Gaussians with sample complexity \(\widetilde{O}(d^8)\). |
---|---|
AbstractList | We present a fairly general framework for reducing \((\varepsilon, \delta)\) differentially private (DP) statistical estimation to its non-private counterpart. As the main application of this framework, we give a polynomial time and \((\varepsilon,\delta)\)-DP algorithm for learning (unrestricted) Gaussian distributions in \(\mathbb{R}^d\). The sample complexity of our approach for learning the Gaussian up to total variation distance \(\alpha\) is \(\widetilde{O}(d^2/\alpha^2 + d^2\sqrt{\ln(1/\delta)}/\alpha \varepsilon + d\ln(1/\delta) / \alpha \varepsilon)\) matching (up to logarithmic factors) the best known information-theoretic (non-efficient) sample complexity upper bound due to Aden-Ali, Ashtiani, and Kamath (ALT'21). In an independent work, Kamath, Mouzakis, Singhal, Steinke, and Ullman (arXiv:2111.04609) proved a similar result using a different approach and with \(O(d^{5/2})\) sample complexity dependence on \(d\). As another application of our framework, we provide the first polynomial time \((\varepsilon, \delta)\)-DP algorithm for robust learning of (unrestricted) Gaussians with sample complexity \(\widetilde{O}(d^{3.5})\). In another independent work, Kothari, Manurangsi, and Velingker (arXiv:2112.03548) also provided a polynomial time \((\varepsilon, \delta)\)-DP algorithm for robust learning of Gaussians with sample complexity \(\widetilde{O}(d^8)\). |
Author | Ashtiani, Hassan Liaw, Christopher |
Author_xml | – sequence: 1 givenname: Hassan surname: Ashtiani fullname: Ashtiani, Hassan – sequence: 2 givenname: Christopher surname: Liaw fullname: Liaw, Christopher |
BookMark | eNqNi8EKgkAURYcoyMp_GGgtjDNp7qNy2aK9TDjayPiezRsD_z6JPqDVhXPO3bAlIJgFi6RSaVIcpFyzmKgTQsj8KLNMRay8efvWwXANNR_QTYC91Y4H28_MtehtePbEG_TcGe3BQsuveiSyGuj7epgJod6xVaMdmfi3W7a_nO-nMhk8vkZDoepw9DCrSuYiTfNMikL9V30A1Rw-HQ |
ContentType | Paper |
Copyright | 2022. This work is published under http://creativecommons.org/licenses/by-sa/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2022. This work is published under http://creativecommons.org/licenses/by-sa/4.0/ (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 Database (Proquest) 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 Database 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_26011652083 |
IEDL.DBID | 8FG |
IngestDate | Wed Sep 25 00:01:29 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_26011652083 |
OpenAccessLink | https://www.proquest.com/docview/2601165208/abstract/?pq-origsite=%requestingapplication% |
PQID | 2601165208 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2601165208 |
PublicationCentury | 2000 |
PublicationDate | 20220622 |
PublicationDateYYYYMMDD | 2022-06-22 |
PublicationDate_xml | – month: 06 year: 2022 text: 20220622 day: 22 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2022 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.3958602 |
SecondaryResourceType | preprint |
Snippet | We present a fairly general framework for reducing \((\varepsilon, \delta)\) differentially private (DP) statistical estimation to its non-private counterpart.... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Complexity Information theory Machine learning Polynomials Upper bounds |
Title | Private and polynomial time algorithms for learning Gaussians and beyond |
URI | https://www.proquest.com/docview/2601165208/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NS8MwFH_MFcGbn_gxR0CvoU3apttJUNoVYaOIwm4jadN5qK5ru4MX_3bzSqsHYccQkkdCeF95v_cDuBe-q5R0PMrV1KUe0w6V2HFI6sxN_TyY-BLByfOFiN-856W_HEDcY2GwrLLXia2izjYp5shtbH3FhM-diS0VZgHSxn4otxT5o_CftSPTOACLYU88xIxHs99sCxeB8Z3dfwq3tSLRMViJLHV1AgP9eQqHbfFlWp9BnFTIMaaJiepJuSm-ECosC4K870QWayO8ef-oifEvScfysCYzuasRAFm3q1QLRDmHuyh8fYppL37VPZV69Xcw9wKGJubXl0Aylqpcq0wKR3pa8ykPGAuE1rlIleeqKxjt2-l6__QNHHGs4ncE5XwEw6ba6VtjWxs1bq9tDNZjuEhezGj-Hf4A8NyGNQ |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV07T8MwED5BKwQbT_EoYAlWi8R2nHZiQKQB2qpDkbpFduKUIaUhTgf-Pb4ohQGps2WfzrLu5fvuA7iXAddaeYIyPeBU-MajCicOKZPxNMjDfqAQnDyeyPhdvM6DeVtws21b5cYmNoY6W6VYI3_A0Ve-DJjXfyy_KLJG4e9qS6GxC13BnetEpHg0_K2xMBm6iJn_M7ON74gOoTtVpamOYMd8HsNe03KZ2hOIpxUyixnicnlSropvBAirgiDbO1HFwgmvP5aWuKiStNwOCzJUa4uwR9vs0g385BTuoufZU0w34pP2gdjkTx1-Bh2X6ZtzIJmf6tzoTElPCWPYgIW-H0pjcplqwfUF9LaddLl9-Rb249l4lIxeJm9XcMCwj9-TlLEedOpqba6dd631TXOFP59Ggpg |
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=Private+and+polynomial+time+algorithms+for+learning+Gaussians+and+beyond&rft.jtitle=arXiv.org&rft.au=Ashtiani%2C+Hassan&rft.au=Liaw%2C+Christopher&rft.date=2022-06-22&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |