RES: Regularized Stochastic BFGS Algorithm

RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method is proposed to solve convex optimization problems with stochastic objectives. The use of stochastic gradient descent algorithms is widespread, but the number of iterations required to approximate...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:arXiv.org
Hlavní autori: Mokhtari, Aryan, Ribeiro, Alejandro
Médium: Paper
Jazyk:English
Vydavateľské údaje: Ithaca Cornell University Library, arXiv.org 29.01.2014
Predmet:
ISSN:2331-8422
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method is proposed to solve convex optimization problems with stochastic objectives. The use of stochastic gradient descent algorithms is widespread, but the number of iterations required to approximate optimal arguments can be prohibitive in high dimensional problems. Application of second order methods, on the other hand, is impracticable because computation of objective function Hessian inverses incurs excessive computational cost. BFGS modifies gradient descent by introducing a Hessian approximation matrix computed from finite gradient differences. RES utilizes stochastic gradients in lieu of deterministic gradients for both, the determination of descent directions and the approximation of the objective function's curvature. Since stochastic gradients can be computed at manageable computational cost RES is realizable and retains the convergence rate advantages of its deterministic counterparts. Convergence results show that lower and upper bounds on the Hessian egeinvalues of the sample functions are sufficient to guarantee convergence to optimal arguments. Numerical experiments showcase reductions in convergence time relative to stochastic gradient descent algorithms and non-regularized stochastic versions of BFGS. An application of RES to the implementation of support vector machines is developed.
AbstractList RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method is proposed to solve convex optimization problems with stochastic objectives. The use of stochastic gradient descent algorithms is widespread, but the number of iterations required to approximate optimal arguments can be prohibitive in high dimensional problems. Application of second order methods, on the other hand, is impracticable because computation of objective function Hessian inverses incurs excessive computational cost. BFGS modifies gradient descent by introducing a Hessian approximation matrix computed from finite gradient differences. RES utilizes stochastic gradients in lieu of deterministic gradients for both, the determination of descent directions and the approximation of the objective function's curvature. Since stochastic gradients can be computed at manageable computational cost RES is realizable and retains the convergence rate advantages of its deterministic counterparts. Convergence results show that lower and upper bounds on the Hessian egeinvalues of the sample functions are sufficient to guarantee convergence to optimal arguments. Numerical experiments showcase reductions in convergence time relative to stochastic gradient descent algorithms and non-regularized stochastic versions of BFGS. An application of RES to the implementation of support vector machines is developed.
Author Mokhtari, Aryan
Ribeiro, Alejandro
Author_xml – sequence: 1
  givenname: Aryan
  surname: Mokhtari
  fullname: Mokhtari, Aryan
– sequence: 2
  givenname: Alejandro
  surname: Ribeiro
  fullname: Ribeiro, Alejandro
BookMark eNotjkFLwzAYQIMoOOfuHgvehNbkS77ki7c5tikMhHX3kTbp1lFbbVoRf70DPb3be--GXbZdGxi7EzxThMgfXf9df2VCcZEZDXjBJiClSEkBXLNZjCfOOWgDiHLCHrbL_CnZhsPYuL7-CT7Jh648ujjUZfK8WufJvDl0fT0c32_ZVeWaGGb_nLLdarlbvKSbt_XrYr5JHQpIyZAiGwpbKJDGAzoLhfReWGMDVVqLQCWSA1MqZY0XqqhAlxWhx4Dn0ym7_9N-9N3nGOKwP3Vj356Le-AEhrThIH8B3nNCqA
ContentType Paper
Copyright 2014. 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: 2014. 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
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
DOI 10.48550/arxiv.1401.7625
DatabaseName ProQuest SciTech Collection
ProQuest Technology Collection
Materials Science & Engineering Collection
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest Central Essentials - QC
ProQuest Central
ProQuest Technology Collection
ProQuest One
ProQuest Central Korea
SciTech Premium Collection
ProQuest Engineering Collection
Engineering Database
Proquest Central Premium
ProQuest One Academic (New)
Publicly Available Content Database
ProQuest One Academic Middle East (New)
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Applied & Life Sciences
ProQuest One Academic (retired)
ProQuest One Academic UKI Edition
ProQuest Central China
Engineering Collection
DatabaseTitle Publicly Available Content Database
Engineering Database
Technology Collection
ProQuest One Academic Middle East (New)
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 One Applied & Life Sciences
ProQuest Engineering Collection
ProQuest One Academic UKI Edition
ProQuest Central Korea
Materials Science & Engineering Collection
ProQuest Central (New)
ProQuest One Academic
ProQuest One Academic (New)
Engineering Collection
DatabaseTitleList Publicly Available Content Database
Database_xml – sequence: 1
  dbid: PIMPY
  name: ProQuest Publicly Available Content Database
  url: http://search.proquest.com/publiccontent
  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
PHGZM
PHGZT
PIMPY
PKEHL
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
ID FETCH-LOGICAL-a512-878489eb9b4237d25a92b3dd1979e8f661e8c58a27c4497d14bf26cf85d5e5233
IEDL.DBID BENPR
IngestDate Mon Jun 30 09:36:01 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a512-878489eb9b4237d25a92b3dd1979e8f661e8c58a27c4497d14bf26cf85d5e5233
Notes SourceType-Working Papers-1
ObjectType-Working Paper/Pre-Print-1
content type line 50
OpenAccessLink https://www.proquest.com/docview/2082786702?pq-origsite=%requestingapplication%
PQID 2082786702
PQPubID 2050157
ParticipantIDs proquest_journals_2082786702
PublicationCentury 2000
PublicationDate 20140129
PublicationDateYYYYMMDD 2014-01-29
PublicationDate_xml – month: 01
  year: 2014
  text: 20140129
  day: 29
PublicationDecade 2010
PublicationPlace Ithaca
PublicationPlace_xml – name: Ithaca
PublicationTitle arXiv.org
PublicationYear 2014
Publisher Cornell University Library, arXiv.org
Publisher_xml – name: Cornell University Library, arXiv.org
SSID ssj0002672553
Score 1.5275116
SecondaryResourceType preprint
Snippet RES, a regularized stochastic version of the Broyden-Fletcher-Goldfarb-Shanno (BFGS) quasi-Newton method is proposed to solve convex optimization problems with...
SourceID proquest
SourceType Aggregation Database
SubjectTerms Algorithms
Approximation
Computational efficiency
Computational geometry
Convergence
Convexity
Curvature
Economic models
Mathematical analysis
Nonlinear programming
Optimization
Quasi Newton methods
Support vector machines
Upper bounds
Title RES: Regularized Stochastic BFGS Algorithm
URI https://www.proquest.com/docview/2082786702
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV09T8MwELWgBYmJb_FRUAYmJJfEcWIfC6KoBQaqqO1QpsrxB60EbUlChfj12CGFAYmFMbIU2cnp3b3z0z2EzjRnxgdJsS1tOXazMDEHwbGAFIwfQsQVLc0mWLfLh0NIqoZbXskql5hYArWaSdcjtySdE8Zj5pOr-St2rlHudrWy0FhFdTepzMZ5vdXuJr3vLguJma2Zw6_7yXJ414XI3ieLpuMVTQsE0S8MLhNLZ_O_W9pC9UTMdbaNVvR0B62Xgk6Z76Jz-2UvvV7pNJ9NPrTy-sVMjoUby-y1Ord97_r5yb6sGL_soUGnPbi5w5UvAhY2PVv84pSDTiF1khZFIgEkDZUKgIHmxiZczWXEBWGSUmAqoKkhsTQ8UpG2vDPcR7XpbKoPkBcERqnYcUQDVOhQhEbEvhHgG8srA3GIGsuTj6rYzkc_xz76e_kYbdjywolcMIEGqhXZmz5Ba3JRTPLstPpVp05t2bdPyf1D8vgJX7eezw
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1JTwIxFH5B0OjJPS6oc9CLyeBMZ2tNjHFDCEuIcNDTpDNtgUQBAXH5T_5HXwfQg4k3Dp6bNO3r277263sAh5IGymKxa2JqS01dC9OkjFOTs4gpy2EeFW7SbCKoVun9Paul4HP6F0bTKqc-MXHUohvrO3IE6ZQE1A8sct57NnXXKP26Om2hMVaLknx_Rcg2OCte4_keEZK_aVwVzElXAZNjcEPrpy5lMmKRJoQI4nFGIkcImwVMUoXhStLYo5wEseuyQNhupIgfK-oJTyJqc3DaOci4qOtWGjK1YqX28H2pQ_wAU3Rn_Bya1Ao74f239iinYUwO_Y73y-UncSy__M8ksII75z3ZX4WU7KzBQkJXjQfrcIx6c2rcyaYm0bY_pDDqw27c4rrotHGZv60bF49NXPuw9bQBjVmsbhPSnW5HboFh20oIXyNgxVwuHe4o7luKM0sharb5NmSngg4nljsIf6S88_fwASwWGpVyWC5WS7uwhImUpvOYhGUhPey_yD2Yj0fD9qC_P9ESA8IZn8oXXUv2XA
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=RES%3A+Regularized+Stochastic+BFGS+Algorithm&rft.jtitle=arXiv.org&rft.au=Mokhtari%2C+Aryan&rft.au=Ribeiro%2C+Alejandro&rft.date=2014-01-29&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422&rft_id=info:doi/10.48550%2Farxiv.1401.7625