Sample size selection in optimization methods for machine learning

This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale machine learning problems. The first part of the paper deals with the delicate issue of dynamic sample selection in the evaluation of the function and gradient. We propose a criterion...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematical programming Ročník 134; číslo 1; s. 127 - 155
Hlavní autoři: Byrd, Richard H., Chin, Gillian M., Nocedal, Jorge, Wu, Yuchen
Médium: Journal Article Konferenční příspěvek
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer-Verlag 01.08.2012
Springer
Springer Nature B.V
Témata:
ISSN:0025-5610, 1436-4646
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale machine learning problems. The first part of the paper deals with the delicate issue of dynamic sample selection in the evaluation of the function and gradient. We propose a criterion for increasing the sample size based on variance estimates obtained during the computation of a batch gradient. We establish an complexity bound on the total cost of a gradient method. The second part of the paper describes a practical Newton method that uses a smaller sample to compute Hessian vector-products than to evaluate the function and the gradient, and that also employs a dynamic sampling technique. The focus of the paper shifts in the third part of the paper to L 1 -regularized problems designed to produce sparse solutions. We propose a Newton-like method that consists of two phases: a (minimalistic) gradient projection phase that identifies zero variables, and subspace phase that applies a subsampled Hessian Newton iteration in the free variables. Numerical tests on speech recognition problems illustrate the performance of the algorithms.
AbstractList Issue Title: Special Issue on ISMP 2012 This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale machine learning problems. The first part of the paper deals with the delicate issue of dynamic sample selection in the evaluation of the function and gradient. We propose a criterion for increasing the sample size based on variance estimates obtained during the computation of a batch gradient. We establish an $${O(1/\epsilon)}$$ complexity bound on the total cost of a gradient method. The second part of the paper describes a practical Newton method that uses a smaller sample to compute Hessian vector-products than to evaluate the function and the gradient, and that also employs a dynamic sampling technique. The focus of the paper shifts in the third part of the paper to L ^sub 1^-regularized problems designed to produce sparse solutions. We propose a Newton-like method that consists of two phases: a (minimalistic) gradient projection phase that identifies zero variables, and subspace phase that applies a subsampled Hessian Newton iteration in the free variables. Numerical tests on speech recognition problems illustrate the performance of the algorithms.[PUBLICATION ABSTRACT]
This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale machine learning problems. The first part of the paper deals with the delicate issue of dynamic sample selection in the evaluation of the function and gradient. We propose a criterion for increasing the sample size based on variance estimates obtained during the computation of a batch gradient. We establish an complexity bound on the total cost of a gradient method. The second part of the paper describes a practical Newton method that uses a smaller sample to compute Hessian vector-products than to evaluate the function and the gradient, and that also employs a dynamic sampling technique. The focus of the paper shifts in the third part of the paper to L 1 -regularized problems designed to produce sparse solutions. We propose a Newton-like method that consists of two phases: a (minimalistic) gradient projection phase that identifies zero variables, and subspace phase that applies a subsampled Hessian Newton iteration in the free variables. Numerical tests on speech recognition problems illustrate the performance of the algorithms.
This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale machine learning problems. The first part of the paper deals with the delicate issue of dynamic sample selection in the evaluation of the function and gradient. We propose a criterion for increasing the sample size based on variance estimates obtained during the computation of a batch gradient. We establish an $${O(1/\epsilon)}$$ complexity bound on the total cost of a gradient method. The second part of the paper describes a practical Newton method that uses a smaller sample to compute Hessian vector-products than to evaluate the function and the gradient, and that also employs a dynamic sampling technique. The focus of the paper shifts in the third part of the paper to L sub(1)-regularized problems designed to produce sparse solutions. We propose a Newton-like method that consists of two phases: a (minimalistic) gradient projection phase that identifies zero variables, and subspace phase that applies a subsampled Hessian Newton iteration in the free variables. Numerical tests on speech recognition problems illustrate the performance of the algorithms.
Author Nocedal, Jorge
Wu, Yuchen
Chin, Gillian M.
Byrd, Richard H.
Author_xml – sequence: 1
  givenname: Richard H.
  surname: Byrd
  fullname: Byrd, Richard H.
  organization: Department of Computer Science, University of Colorado
– sequence: 2
  givenname: Gillian M.
  surname: Chin
  fullname: Chin, Gillian M.
  organization: Department of Industrial Engineering and Management Sciences, Northwestern University
– sequence: 3
  givenname: Jorge
  surname: Nocedal
  fullname: Nocedal, Jorge
  email: nocedal@eecs.northwestern.edu
  organization: Department of Industrial Engineering and Management Sciences, Northwestern University
– sequence: 4
  givenname: Yuchen
  surname: Wu
  fullname: Wu, Yuchen
  organization: Google Inc
BackLink http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=26294228$$DView record in Pascal Francis
BookMark eNp9kUtLAzEUhYNUsFZ_gLsBEdyM3rw7SxVfUHChrkOaybQpM0lNpgv7600fggi6uZcL3zkc7jlGAx-8RegMwxUGkNcJAwZZAiYlcElKfoCGmFFRMsHEAA0BCC-5wHCEjlNaAACm4_EQ3b7qbtnaIrl1Hra1pnfBF84XYdm7zq319u5sPw91KpoQi06bufO2aK2O3vnZCTpsdJvs6X6P0PvD_dvdUzl5eXy-u5mUhsqqL2uBGy2gJmBpzUhDrdCmNqzhUw2GacFhPKVTzZioeI1BSC4Fz4y0AJXhdIQud77LGD5WNvWqc8nYttXehlVSmFWM4gpwldHzX-girKLP6RQGCpIAZixTF3tKJ6PbJmpvXFLL6DodPxURpGKEjDMnd5yJIaVoG2Vcv_1LH7Vrs6XadKB2Hajcgdp0oDaR8S_lt_l_GrLTpMz6mY0_s_8l-gKX15lJ
CODEN MHPGA4
CitedBy_id crossref_primary_10_1007_s10957_025_02621_8
crossref_primary_10_1007_s41060_025_00832_w
crossref_primary_10_1007_s12145_024_01268_9
crossref_primary_10_1088_1742_6596_2131_4_042071
crossref_primary_10_1007_s10107_017_1137_4
crossref_primary_10_1109_JSEN_2024_3408323
crossref_primary_10_1093_imanum_drac083
crossref_primary_10_1016_j_compind_2021_103546
crossref_primary_10_32604_cmc_2023_039683
crossref_primary_10_1007_s10107_022_01859_8
crossref_primary_10_1016_j_eswa_2023_121556
crossref_primary_10_1007_s11565_022_00435_4
crossref_primary_10_1007_s40305_019_00276_7
crossref_primary_10_1137_17M1143319
crossref_primary_10_2478_caim_2020_0002
crossref_primary_10_1016_j_rsase_2025_101552
crossref_primary_10_1016_j_rineng_2023_100973
crossref_primary_10_1109_TPAMI_2018_2889774
crossref_primary_10_1016_j_cma_2022_115278
crossref_primary_10_1080_24725854_2018_1448489
crossref_primary_10_1016_j_engappai_2018_03_017
crossref_primary_10_1137_17M1125157
crossref_primary_10_1016_j_ultras_2022_106854
crossref_primary_10_1007_s11425_020_1865_1
crossref_primary_10_1007_s10489_022_04206_8
crossref_primary_10_1109_TSP_2022_3186526
crossref_primary_10_1080_02331934_2017_1359590
crossref_primary_10_1080_10556788_2017_1296439
crossref_primary_10_1016_j_neunet_2017_06_003
crossref_primary_10_1093_bib_bbac327
crossref_primary_10_1007_s10589_025_00667_y
crossref_primary_10_1007_s10957_023_02334_w
crossref_primary_10_1109_TAC_2023_3290121
crossref_primary_10_3390_info14040223
crossref_primary_10_1109_MSP_2020_3003539
crossref_primary_10_1109_TAC_2016_2539225
crossref_primary_10_1214_25_AOAS2013
crossref_primary_10_1137_130915984
crossref_primary_10_1137_19M1288802
crossref_primary_10_1155_dth_1996661
crossref_primary_10_1007_s10589_017_9891_z
crossref_primary_10_1007_s11075_017_0290_4
crossref_primary_10_1155_2021_9991859
crossref_primary_10_1007_s10589_013_9553_8
crossref_primary_10_1109_MCOMSTD_0004_2200076
crossref_primary_10_1088_1361_6420_aa9a90
crossref_primary_10_1137_14098171X
crossref_primary_10_1080_10556788_2024_2346834
crossref_primary_10_1080_10556788_2016_1138222
crossref_primary_10_1007_s10898_020_00921_z
crossref_primary_10_1002_oca_3109
crossref_primary_10_1007_s10898_018_0682_6
crossref_primary_10_1016_j_ifacol_2020_12_2284
crossref_primary_10_1287_moor_2021_0068
crossref_primary_10_1007_s40430_022_03920_1
crossref_primary_10_1016_j_eswa_2022_117719
crossref_primary_10_1137_15M1038049
crossref_primary_10_3390_math10193595
crossref_primary_10_1007_s10107_023_01935_7
crossref_primary_10_1080_19475705_2024_2383783
crossref_primary_10_1177_03611981221150923
crossref_primary_10_5812_iranjradiol_119266
crossref_primary_10_1214_21_AOAS1481
crossref_primary_10_1016_j_procs_2018_08_199
crossref_primary_10_1109_TNNLS_2023_3280826
crossref_primary_10_1137_140961791
crossref_primary_10_1007_s10107_015_0941_y
crossref_primary_10_1007_s10208_021_09513_z
crossref_primary_10_1007_s11750_024_00673_z
crossref_primary_10_1109_JSTSP_2015_2505684
crossref_primary_10_1016_j_dajour_2023_100172
crossref_primary_10_1109_TCSII_2020_3012386
crossref_primary_10_1186_s12911_023_02155_x
crossref_primary_10_1007_s00500_020_05262_3
crossref_primary_10_1080_10556788_2015_1025403
crossref_primary_10_1007_s10586_025_05388_9
crossref_primary_10_1109_TSP_2022_3219993
crossref_primary_10_1007_s12532_023_00233_9
crossref_primary_10_1007_s10107_018_1297_x
crossref_primary_10_1137_17M1144799
crossref_primary_10_1016_j_rineng_2024_102483
crossref_primary_10_1136_bmjopen_2020_037161
crossref_primary_10_1016_j_procs_2015_04_028
crossref_primary_10_1137_18M1181249
crossref_primary_10_1007_s10589_020_00196_w
crossref_primary_10_1017_S0962492919000059
crossref_primary_10_1137_15M1031953
crossref_primary_10_1080_10556788_2019_1658107
crossref_primary_10_1016_j_amc_2021_126486
crossref_primary_10_1109_ACCESS_2022_3199021
crossref_primary_10_1016_j_sorms_2014_05_001
crossref_primary_10_1007_s10915_022_02084_3
crossref_primary_10_1093_imanum_dry009
crossref_primary_10_1016_j_cam_2024_116182
crossref_primary_10_1109_TPAMI_2018_2876413
crossref_primary_10_1016_j_neuroimage_2018_10_054
crossref_primary_10_1080_10556788_2020_1852403
crossref_primary_10_1007_s10107_018_1346_5
crossref_primary_10_1137_140954362
crossref_primary_10_1016_j_knosys_2020_106626
crossref_primary_10_1093_imanum_drae110
crossref_primary_10_1137_19M1302211
crossref_primary_10_1016_j_tbs_2022_01_001
crossref_primary_10_1214_18_AOS1707
crossref_primary_10_1177_00405175231184639
crossref_primary_10_1109_TAC_2024_3379387
crossref_primary_10_1007_s10107_023_01999_5
crossref_primary_10_1080_10556788_2025_2547397
crossref_primary_10_3390_molecules25133025
crossref_primary_10_1093_imanum_drad020
crossref_primary_10_1109_JPROC_2020_3021381
crossref_primary_10_1287_moor_2022_0136
crossref_primary_10_1007_s10957_024_02509_z
crossref_primary_10_1007_s11075_014_9869_1
crossref_primary_10_1016_j_ijpe_2016_08_032
crossref_primary_10_1080_23302674_2019_1574365
crossref_primary_10_1038_s41598_024_83617_8
crossref_primary_10_1137_16M1080173
crossref_primary_10_1007_s11590_014_0795_x
crossref_primary_10_1088_1361_6420_adc0b7
crossref_primary_10_3934_naco_2025022
crossref_primary_10_1016_j_neucom_2019_07_070
crossref_primary_10_1038_s41534_022_00592_6
crossref_primary_10_1007_s11063_022_11057_4
crossref_primary_10_1287_opre_2019_1946
crossref_primary_10_1080_17477778_2024_2420807
crossref_primary_10_1016_j_jcp_2023_112523
crossref_primary_10_1016_j_aml_2024_109053
crossref_primary_10_1134_S0965542524702002
crossref_primary_10_1016_j_cie_2022_108656
crossref_primary_10_1016_j_bbagrm_2024_195062
crossref_primary_10_1007_s10107_023_01941_9
crossref_primary_10_1007_s10287_024_00528_9
crossref_primary_10_1002_oa_2883
crossref_primary_10_1007_s40996_024_01401_0
crossref_primary_10_1007_s40305_023_00453_9
crossref_primary_10_1007_s10589_025_00720_w
crossref_primary_10_1007_s10115_017_1108_3
crossref_primary_10_1007_s10915_024_02748_2
crossref_primary_10_1016_j_cam_2024_116083
crossref_primary_10_1090_mcom_3802
crossref_primary_10_1007_s10107_015_0965_3
crossref_primary_10_1111_insr_12030
crossref_primary_10_1080_10556788_2024_2322700
crossref_primary_10_1137_18M1216250
crossref_primary_10_1007_s40305_025_00599_8
crossref_primary_10_1080_13658816_2021_1931237
crossref_primary_10_1016_j_engappai_2018_11_001
crossref_primary_10_1016_j_jobe_2022_105674
crossref_primary_10_1137_140951679
crossref_primary_10_1190_geo2018_0624_1
crossref_primary_10_1007_s10957_025_02817_y
crossref_primary_10_1080_10556788_2019_1624747
crossref_primary_10_1287_ijoo_2018_0010
crossref_primary_10_1007_s42045_018_0009_7
crossref_primary_10_1016_j_cma_2022_115371
crossref_primary_10_1093_imanum_drz027
crossref_primary_10_1007_s10107_022_01913_5
crossref_primary_10_3390_s21113655
crossref_primary_10_1038_s41467_021_22756_2
crossref_primary_10_1007_s10107_022_01846_z
crossref_primary_10_1287_ijoc_2017_0771
crossref_primary_10_1109_JIOT_2023_3237806
crossref_primary_10_1016_j_ins_2020_12_075
crossref_primary_10_1137_17M1154679
crossref_primary_10_1016_j_ejco_2024_100088
crossref_primary_10_1016_j_camwa_2023_09_014
crossref_primary_10_1007_s00500_020_05219_6
crossref_primary_10_1137_19M1291832
Cites_doi 10.1109/TAC.1976.1101194
10.1109/18.382009
10.1016/0041-5553(69)90035-4
10.1137/S1052623498345075
10.1214/aoms/1177729586
10.1145/858481.858483
10.1109/TSP.2009.2016892
10.1007/s00211-004-0569-y
10.1137/0728030
10.1007/s10287-005-0044-y
10.1137/080716542
10.1287/moor.21.3.615
10.1137/S1052623498349541
10.1137/0330046
10.1109/JSTSP.2007.910281
10.1007/s10107-007-0149-x
10.1007/s10107-007-0164-y
10.1137/S1052623499363220
10.1109/CDC.2012.6426626
10.1145/1273496.1273501
10.1145/1143844.1143966
10.1137/10079923X
10.1137/050635225
ContentType Journal Article
Conference Proceeding
Copyright Springer and Mathematical Optimization Society 2012
2014 INIST-CNRS
Copyright_xml – notice: Springer and Mathematical Optimization Society 2012
– notice: 2014 INIST-CNRS
DBID AAYXX
CITATION
IQODW
3V.
7SC
7WY
7WZ
7XB
87Z
88I
8AL
8AO
8FD
8FE
8FG
8FK
8FL
ABJCF
ABUWG
AFKRA
ARAPS
AZQEC
BENPR
BEZIV
BGLVJ
CCPQU
DWQXO
FRNLG
F~G
GNUQQ
HCIFZ
JQ2
K60
K6~
K7-
L.-
L.0
L6V
L7M
L~C
L~D
M0C
M0N
M2P
M7S
P5Z
P62
PHGZM
PHGZT
PKEHL
PQBIZ
PQBZA
PQEST
PQGLB
PQQKQ
PQUKI
PRINS
PTHSS
Q9U
DOI 10.1007/s10107-012-0572-5
DatabaseName CrossRef
Pascal-Francis
ProQuest Central (Corporate)
Computer and Information Systems Abstracts
ABI/INFORM Collection
ABI/INFORM Global (PDF only)
ProQuest Central (purchase pre-March 2016)
ABI/INFORM Collection
Science Database (Alumni Edition)
Computing Database (Alumni Edition)
ProQuest Pharma Collection
Technology Research Database
ProQuest SciTech Collection
ProQuest Technology Collection
ProQuest Central (Alumni) (purchase pre-March 2016)
ABI/INFORM Collection (Alumni)
ProQuest SciTech Premium Collection Technology Collection Materials Science & Engineering Database
ProQuest Central (Alumni)
ProQuest Central UK/Ireland
ProQuest SciTech Premium Collection Technology Collection Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Central
Business Premium Collection
ProQuest Technology Collection
ProQuest One Community College
ProQuest Central Korea
Business Premium Collection (Alumni)
ABI/INFORM Global (Corporate)
ProQuest Central Student
SciTech Premium Collection
ProQuest Computer Science Collection
ProQuest Business Collection (Alumni Edition)
ProQuest Business Collection
Computer Science Database
ABI/INFORM Professional Advanced
ABI/INFORM Professional Standard
ProQuest Engineering Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
ABI/INFORM Global
Computing Database
Science Database (ProQuest)
Engineering Database
Advanced Technologies & Aerospace Database
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Premium
ProQuest One Academic (New)
ProQuest One Academic Middle East (New)
ProQuest One Business
ProQuest One Business (Alumni)
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
ProQuest Central Basic
DatabaseTitle CrossRef
ProQuest Business Collection (Alumni Edition)
Computer Science Database
ProQuest Central Student
ProQuest Advanced Technologies & Aerospace Collection
ProQuest Central Essentials
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
SciTech Premium Collection
ProQuest Central China
ABI/INFORM Complete
ProQuest One Applied & Life Sciences
ProQuest Central (New)
Engineering Collection
Advanced Technologies & Aerospace Collection
Business Premium Collection
ABI/INFORM Global
Engineering Database
ProQuest Science Journals (Alumni Edition)
ProQuest One Academic Eastern Edition
ProQuest Technology Collection
ProQuest Business Collection
ProQuest One Academic UKI Edition
ProQuest One Academic
ProQuest One Academic (New)
ABI/INFORM Global (Corporate)
ProQuest One Business
Technology Collection
Technology Research Database
Computer and Information Systems Abstracts – Academic
ProQuest One Academic Middle East (New)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest Pharma Collection
ProQuest Central
ABI/INFORM Professional Advanced
ProQuest Engineering Collection
ABI/INFORM Professional Standard
ProQuest Central Korea
Advanced Technologies Database with Aerospace
ABI/INFORM Complete (Alumni Edition)
ProQuest Computing
ABI/INFORM Global (Alumni Edition)
ProQuest Central Basic
ProQuest Science Journals
ProQuest Computing (Alumni Edition)
ProQuest SciTech Collection
Computer and Information Systems Abstracts Professional
Advanced Technologies & Aerospace Database
Materials Science & Engineering Collection
ProQuest One Business (Alumni)
ProQuest Central (Alumni)
Business Premium Collection (Alumni)
DatabaseTitleList ProQuest Business Collection (Alumni Edition)

Computer and Information Systems Abstracts
Database_xml – sequence: 1
  dbid: BENPR
  name: ProQuest Central
  url: https://www.proquest.com/central
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Mathematics
Applied Sciences
EISSN 1436-4646
EndPage 155
ExternalDocumentID 2726562611
26294228
10_1007_s10107_012_0572_5
Genre Feature
GroupedDBID --K
--Z
-52
-5D
-5G
-BR
-EM
-Y2
-~C
-~X
.4S
.86
.DC
.VR
06D
0R~
0VY
199
1B1
1N0
1OL
1SB
203
28-
29M
2J2
2JN
2JY
2KG
2KM
2LR
2P1
2VQ
2~H
30V
3V.
4.4
406
408
409
40D
40E
5GY
5QI
5VS
67Z
6NX
6TJ
78A
7WY
88I
8AO
8FE
8FG
8FL
8TC
8UJ
8VB
95-
95.
95~
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBBX
ABBXA
ABDBF
ABDZT
ABECU
ABFTV
ABHLI
ABHQN
ABJCF
ABJNI
ABJOX
ABKCH
ABKTR
ABMNI
ABMQK
ABNWP
ABQBU
ABQSL
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABUWG
ABWNU
ABXPI
ACAOD
ACBXY
ACDTI
ACGFS
ACGOD
ACHSB
ACHXU
ACIWK
ACKNC
ACMDZ
ACMLO
ACNCT
ACOKC
ACOMO
ACPIV
ACUHS
ACZOJ
ADHHG
ADHIR
ADIMF
ADINQ
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFIE
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMOZ
AEMSY
AENEX
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFEXP
AFFNX
AFGCZ
AFKRA
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGGDS
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWIL
AGWZB
AGYKE
AHAVH
AHBYD
AHKAY
AHQJS
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
AKVCP
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
AOCGG
ARAPS
ARCSS
ARMRJ
ASPBG
AVWKF
AXYYD
AYJHY
AZFZN
AZQEC
B-.
B0M
BA0
BAPOH
BBWZM
BDATZ
BENPR
BEZIV
BGLVJ
BGNMA
BPHCQ
BSONS
CAG
CCPQU
COF
CS3
CSCUP
DDRTE
DL5
DNIVK
DPUIP
DU5
DWQXO
EAD
EAP
EBA
EBLON
EBR
EBS
EBU
ECS
EDO
EIOEI
EJD
EMI
EMK
EPL
ESBYG
EST
ESX
FEDTE
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRNLG
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNUQQ
GNWQR
GQ6
GQ7
GQ8
GROUPED_ABI_INFORM_COMPLETE
GXS
H13
HCIFZ
HF~
HG5
HG6
HMJXF
HQYDN
HRMNR
HVGLF
HZ~
H~9
I-F
I09
IAO
IHE
IJ-
IKXTQ
ITM
IWAJR
IXC
IZIGR
IZQ
I~X
I~Z
J-C
J0Z
JBSCW
JCJTX
JZLTJ
K1G
K60
K6V
K6~
K7-
KDC
KOV
KOW
L6V
LAS
LLZTM
M0C
M0N
M2P
M4Y
M7S
MA-
N2Q
N9A
NB0
NDZJH
NPVJJ
NQ-
NQJWS
NU0
O9-
O93
O9G
O9I
O9J
OAM
P19
P2P
P62
P9R
PF0
PQBIZ
PQBZA
PQQKQ
PROAC
PT4
PT5
PTHSS
Q2X
QOK
QOS
QWB
R4E
R89
R9I
RHV
RIG
RNI
RNS
ROL
RPX
RPZ
RSV
RZK
S16
S1Z
S26
S27
S28
S3B
SAP
SCLPG
SDD
SDH
SDM
SHX
SISQX
SJYHP
SMT
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
SZN
T13
T16
TH9
TN5
TSG
TSK
TSV
TUC
TUS
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W23
W48
WH7
WK8
XPP
YLTOR
Z45
Z5O
Z7R
Z7S
Z7X
Z7Y
Z7Z
Z81
Z83
Z86
Z88
Z8M
Z8N
Z8R
Z8T
Z8W
Z92
ZL0
ZMTXR
ZWQNP
~02
~8M
~EX
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABRTQ
ACSTC
ADHKG
ADXHL
AEZWR
AFDZB
AFFHD
AFHIU
AFOHR
AGQPQ
AHPBZ
AHWEU
AIXLP
AMVHM
ATHPR
AYFIA
CITATION
PHGZM
PHGZT
PQGLB
IQODW
7SC
7XB
8AL
8FD
8FK
JQ2
L.-
L.0
L7M
L~C
L~D
PKEHL
PQEST
PQUKI
PRINS
PUEGO
Q9U
ID FETCH-LOGICAL-c379t-d61fa60d20e3d42f3e6acdc4f5ba0c4a6508b3ba44695d106757656ac7e009c53
IEDL.DBID M2P
ISICitedReferencesCount 247
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000306493800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0025-5610
IngestDate Thu Sep 04 20:21:38 EDT 2025
Thu Sep 25 00:49:17 EDT 2025
Mon Jul 21 09:16:13 EDT 2025
Sat Nov 29 05:49:02 EST 2025
Tue Nov 18 20:40:21 EST 2025
Fri Feb 21 02:32:41 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Keywords 65K05
49M15
49M37
Costs
Sample size
Iterative method
Non linear programming
Lot sizing
Dimensioning
Function evaluation
Vector space
Learning (artificial intelligence)
Batch process
Speech recognition
Batch production
Sampling
Newton method
Gradient method
Mathematical programming
Large scale system
Language English
License http://www.springer.com/tdm
CC BY 4.0
LinkModel DirectLink
MeetingName Special issue of the ISMP 2012 Berlin
MergedId FETCHMERGED-LOGICAL-c379t-d61fa60d20e3d42f3e6acdc4f5ba0c4a6508b3ba44695d106757656ac7e009c53
Notes SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
PQID 1030720144
PQPubID 25307
PageCount 29
ParticipantIDs proquest_miscellaneous_1494319019
proquest_journals_1030720144
pascalfrancis_primary_26294228
crossref_citationtrail_10_1007_s10107_012_0572_5
crossref_primary_10_1007_s10107_012_0572_5
springer_journals_10_1007_s10107_012_0572_5
PublicationCentury 2000
PublicationDate 2012-08-01
PublicationDateYYYYMMDD 2012-08-01
PublicationDate_xml – month: 08
  year: 2012
  text: 2012-08-01
  day: 01
PublicationDecade 2010
PublicationPlace Berlin/Heidelberg
PublicationPlace_xml – name: Berlin/Heidelberg
– name: Heidelberg
PublicationSubtitle A Publication of the Mathematical Optimization Society
PublicationTitle Mathematical programming
PublicationTitleAbbrev Math. Program
PublicationYear 2012
Publisher Springer-Verlag
Springer
Springer Nature B.V
Publisher_xml – name: Springer-Verlag
– name: Springer
– name: Springer Nature B.V
References Shapiro, Homem-de-Mello (CR28) 1998; 81
Shapiro, Homem-de-Mello (CR29) 2000; 11
CR13
Freund (CR16) 1962
CR32
Agarwal, Duchi (CR1) 2011; arXiv
Dekel, Gilad-Bachrach, Shamir, Xiao (CR10) 2010; arXiv
CR31
Niu, Recht, Ré, Wright (CR24) 2011; arXiv
Wright, Nowak, Figueiredo (CR33) 2009; 57
Figueiredo, Nowak, Wright (CR15) 2007; 1
Bertsekas (CR5) 1976; AC-21
Duchi, Singer (CR14) 2009; 10
Friedlander, Schmidt (CR17) 2011; arXiv
Shapiro, Wardi (CR30) 1996; 21
Byrd, Chin, Neveitt, Nocedal (CR7) 2011; 21
Hager, Zhang (CR18) 2007; 17
Robbins, Monro (CR27) 1951; 22
Kleywegt, Shapiro, Homem-de-Mello (CR20) 2001; 12
Lin, Moré (CR21) 1999; 9
CR2
Xiao (CR34) 2010; 9999
Polyak, Juditsky (CR25) 1992; 30
Bottou, Bousquet, Platt, Koller, Singer, Roweis (CR6) 2008
Deng, Ferris (CR11) 2009; 117
CR22
Donoho (CR12) 1995; 41
Nesterov (CR23) 2009; 120
Bastin, Cirillo, Toint (CR3) 2006; 3
Dai, Fletcher (CR9) 2005; 100
Beck, Teboulle (CR4) 2009; 2
Polyak (CR26) 1969; 9
Homem-de-Mello (CR19) 2003; 13
Conn, Gould, Toint (CR8) 1991; 28
572_CR24
572_CR1
A.R. Conn (572_CR8) 1991; 28
M. Figueiredo (572_CR15) 2007; 1
572_CR2
D.P. Bertsekas (572_CR5) 1976; AC-21
572_CR7
B.T. Polyak (572_CR26) 1969; 9
L. Xiao (572_CR34) 2010; 9999
W.W. Hager (572_CR18) 2007; 17
L. Bottou (572_CR6) 2008
A.J. Kleywegt (572_CR20) 2001; 12
572_CR10
572_CR32
572_CR31
B. Polyak (572_CR25) 1992; 30
572_CR13
C. Lin (572_CR21) 1999; 9
572_CR17
A. Shapiro (572_CR29) 2000; 11
S. Wright (572_CR33) 2009; 57
D. Donoho (572_CR12) 1995; 41
A. Shapiro (572_CR30) 1996; 21
A. Beck (572_CR4) 2009; 2
G. Deng (572_CR11) 2009; 117
F. Bastin (572_CR3) 2006; 3
H. Robbins (572_CR27) 1951; 22
A. Shapiro (572_CR28) 1998; 81
Y. Dai (572_CR9) 2005; 100
J.E. Freund (572_CR16) 1962
T. Homem-de-Mello (572_CR19) 2003; 13
J. Duchi (572_CR14) 2009; 10
Y. Nesterov (572_CR23) 2009; 120
572_CR22
References_xml – ident: CR22
– ident: CR2
– volume: AC-21
  start-page: 174
  year: 1976
  end-page: 184
  ident: CR5
  article-title: On the Goldstein-Levitin-Poljak gradient projection method
  publication-title: IEEE Trans. Autom. Control
  doi: 10.1109/TAC.1976.1101194
– volume: 41
  start-page: 613
  issue: 3
  year: 1995
  end-page: 627
  ident: CR12
  article-title: De-noising by soft-thresholding
  publication-title: Inf. Theory IEEE Trans.
  doi: 10.1109/18.382009
– volume: arXiv
  start-page: 1104
  year: 2011
  end-page: 5525
  ident: CR1
  article-title: Distributed delayed stochastic optimization
  publication-title: Arxiv preprint
– volume: 21
  start-page: 977
  issue: 3
  year: 2011
  end-page: 995
  ident: CR7
  article-title: On the use of stochastic Hessian information in unconstrained optimization
  publication-title: SIAM J. Optim.
– volume: 9
  start-page: 94
  year: 1969
  end-page: 112
  ident: CR26
  article-title: The conjugate gradient method in extremal problems
  publication-title: USSR Comput. Math. Math. Phys.
  doi: 10.1016/0041-5553(69)90035-4
– start-page: 161
  year: 2008
  end-page: 168
  ident: CR6
  article-title: The tradeoffs of large scale learning
  publication-title: Advances in Neural Information Processing Systems, vol. 20
– volume: 9
  start-page: 1100
  issue: 4
  year: 1999
  end-page: 1127
  ident: CR21
  article-title: Newton’s method for large bound-constrained optimization problems
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623498345075
– volume: 22
  start-page: 400
  issue: 3
  year: 1951
  end-page: 407
  ident: CR27
  article-title: A stochastic approximation method
  publication-title: Ann. Math. Stat.
  doi: 10.1214/aoms/1177729586
– volume: 13
  start-page: 108
  issue: 2
  year: 2003
  end-page: 133
  ident: CR19
  article-title: Variable-sample methods for stochastic optimization
  publication-title: ACM Trans. Model. Comput. Simul.
  doi: 10.1145/858481.858483
– volume: 57
  start-page: 2479
  issue: 7
  year: 2009
  end-page: 2493
  ident: CR33
  article-title: Sparse reconstruction by separable approximation
  publication-title: Signal Process. IEEE Trans.
  doi: 10.1109/TSP.2009.2016892
– volume: 9999
  start-page: 2543
  year: 2010
  end-page: 2596
  ident: CR34
  article-title: Dual averaging methods for regularized stochastic learning and online optimization
  publication-title: J. Mach. Learn. Res.
– volume: 100
  start-page: 21
  issue: 1
  year: 2005
  end-page: 47
  ident: CR9
  article-title: Projected Barzilai-Borwein methods for large-scale box-constrained quadratic programming
  publication-title: Numerische Mathematik
  doi: 10.1007/s00211-004-0569-y
– volume: arXiv
  start-page: 1104
  year: 2011
  end-page: 2373
  ident: CR17
  article-title: Hybrid deterministic-stochastic methods for data fitting
  publication-title: Arxiv preprint
– volume: 28
  start-page: 545
  issue: 2
  year: 1991
  end-page: 572
  ident: CR8
  article-title: A globally convergent augmented Lagrangian algorithm for optimization with general constraints and simple bounds
  publication-title: SIAM J. Numer. Anal.
  doi: 10.1137/0728030
– volume: 3
  start-page: 55
  issue: 1
  year: 2006
  end-page: 79
  ident: CR3
  article-title: An adaptive monte carlo algorithm for computing mixed logit estimators
  publication-title: Comput. Manag. Sci.
  doi: 10.1007/s10287-005-0044-y
– volume: 2
  start-page: 183
  issue: 1
  year: 2009
  end-page: 202
  ident: CR4
  article-title: A fast iterative shrinkage-thresholding algorithm for linear inverse problems
  publication-title: SIAM J. Imaging Sci.
  doi: 10.1137/080716542
– volume: 81
  start-page: 301
  year: 1998
  end-page: 325
  ident: CR28
  article-title: A simulation-based approach to two-stage stochastic programming with recourse
  publication-title: Math. Program.
– volume: 21
  start-page: 615
  issue: 3
  year: 1996
  end-page: 628
  ident: CR30
  article-title: Convergence of stochastic algorithms
  publication-title: Math. Oper. Res.
  doi: 10.1287/moor.21.3.615
– ident: CR31
– ident: CR13
– volume: 11
  start-page: 70
  issue: 1
  year: 2000
  end-page: 86
  ident: CR29
  article-title: On the rate of convergence of optimal solutions of monte carlo approximations of stochastic programs
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623498349541
– year: 1962
  ident: CR16
  publication-title: Mathematical Statistics
– ident: CR32
– volume: 10
  start-page: 2899
  year: 2009
  end-page: 2934
  ident: CR14
  article-title: Efficient online and batch learning using forward backward splitting
  publication-title: J. Mach. Learn. Res.
– volume: 30
  start-page: 838
  year: 1992
  ident: CR25
  article-title: Acceleration of stochastic approximation by averaging
  publication-title: SIAM J. Control Optim.
  doi: 10.1137/0330046
– volume: 1
  start-page: 586
  issue: 4
  year: 2007
  end-page: 597
  ident: CR15
  article-title: Gradient projection for sparse reconstruction: Application to compressed sensing and other inverse problems
  publication-title: IEEE J. Sel. Top. Signal Process.
  doi: 10.1109/JSTSP.2007.910281
– volume: arXiv
  start-page: 1106
  year: 2011
  end-page: 5730
  ident: CR24
  article-title: Hogwild!: a lock-free approach to parallelizing stochastic gradient descent
  publication-title: Arxiv preprint
– volume: arXiv
  start-page: 1012
  year: 2010
  end-page: 1367
  ident: CR10
  article-title: Optimal distributed online prediction using mini-batches
  publication-title: Arxiv preprint
– volume: 120
  start-page: 221
  issue: 1
  year: 2009
  end-page: 259
  ident: CR23
  article-title: Primal-dual subgradient methods for convex problems
  publication-title: Math. Program.
  doi: 10.1007/s10107-007-0149-x
– volume: 117
  start-page: 81
  issue: 1–2
  year: 2009
  end-page: 109
  ident: CR11
  article-title: Variable-number sample-path optimization
  publication-title: Math. Program.
  doi: 10.1007/s10107-007-0164-y
– volume: 12
  start-page: 479
  issue: 2
  year: 2001
  end-page: 502
  ident: CR20
  article-title: The sample average approximation method for stochastic discrete optimization
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623499363220
– volume: 17
  start-page: 526
  issue: 2
  year: 2007
  end-page: 557
  ident: CR18
  article-title: A new active set algorithm for box constrained optimization
  publication-title: SIOPT
– volume: 9
  start-page: 94
  year: 1969
  ident: 572_CR26
  publication-title: USSR Comput. Math. Math. Phys.
  doi: 10.1016/0041-5553(69)90035-4
– volume: 30
  start-page: 838
  year: 1992
  ident: 572_CR25
  publication-title: SIAM J. Control Optim.
  doi: 10.1137/0330046
– volume: AC-21
  start-page: 174
  year: 1976
  ident: 572_CR5
  publication-title: IEEE Trans. Autom. Control
  doi: 10.1109/TAC.1976.1101194
– volume-title: Mathematical Statistics
  year: 1962
  ident: 572_CR16
– volume: 2
  start-page: 183
  issue: 1
  year: 2009
  ident: 572_CR4
  publication-title: SIAM J. Imaging Sci.
  doi: 10.1137/080716542
– volume: 28
  start-page: 545
  issue: 2
  year: 1991
  ident: 572_CR8
  publication-title: SIAM J. Numer. Anal.
  doi: 10.1137/0728030
– volume: 100
  start-page: 21
  issue: 1
  year: 2005
  ident: 572_CR9
  publication-title: Numerische Mathematik
  doi: 10.1007/s00211-004-0569-y
– volume: 1
  start-page: 586
  issue: 4
  year: 2007
  ident: 572_CR15
  publication-title: IEEE J. Sel. Top. Signal Process.
  doi: 10.1109/JSTSP.2007.910281
– volume: 3
  start-page: 55
  issue: 1
  year: 2006
  ident: 572_CR3
  publication-title: Comput. Manag. Sci.
  doi: 10.1007/s10287-005-0044-y
– volume: 12
  start-page: 479
  issue: 2
  year: 2001
  ident: 572_CR20
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623499363220
– volume: 41
  start-page: 613
  issue: 3
  year: 1995
  ident: 572_CR12
  publication-title: Inf. Theory IEEE Trans.
  doi: 10.1109/18.382009
– ident: 572_CR17
– ident: 572_CR13
– volume: 9
  start-page: 1100
  issue: 4
  year: 1999
  ident: 572_CR21
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623498345075
– ident: 572_CR32
– volume: 11
  start-page: 70
  issue: 1
  year: 2000
  ident: 572_CR29
  publication-title: SIAM J. Optim.
  doi: 10.1137/S1052623498349541
– volume: 9999
  start-page: 2543
  year: 2010
  ident: 572_CR34
  publication-title: J. Mach. Learn. Res.
– volume: 117
  start-page: 81
  issue: 1–2
  year: 2009
  ident: 572_CR11
  publication-title: Math. Program.
  doi: 10.1007/s10107-007-0164-y
– ident: 572_CR1
  doi: 10.1109/CDC.2012.6426626
– volume: 13
  start-page: 108
  issue: 2
  year: 2003
  ident: 572_CR19
  publication-title: ACM Trans. Model. Comput. Simul.
  doi: 10.1145/858481.858483
– volume: 22
  start-page: 400
  issue: 3
  year: 1951
  ident: 572_CR27
  publication-title: Ann. Math. Stat.
  doi: 10.1214/aoms/1177729586
– ident: 572_CR2
  doi: 10.1145/1273496.1273501
– volume: 10
  start-page: 2899
  year: 2009
  ident: 572_CR14
  publication-title: J. Mach. Learn. Res.
– volume: 120
  start-page: 221
  issue: 1
  year: 2009
  ident: 572_CR23
  publication-title: Math. Program.
  doi: 10.1007/s10107-007-0149-x
– ident: 572_CR22
– ident: 572_CR24
– start-page: 161
  volume-title: Advances in Neural Information Processing Systems, vol. 20
  year: 2008
  ident: 572_CR6
– volume: 57
  start-page: 2479
  issue: 7
  year: 2009
  ident: 572_CR33
  publication-title: Signal Process. IEEE Trans.
  doi: 10.1109/TSP.2009.2016892
– ident: 572_CR31
  doi: 10.1145/1143844.1143966
– volume: 81
  start-page: 301
  year: 1998
  ident: 572_CR28
  publication-title: Math. Program.
– ident: 572_CR7
  doi: 10.1137/10079923X
– volume: 21
  start-page: 615
  issue: 3
  year: 1996
  ident: 572_CR30
  publication-title: Math. Oper. Res.
  doi: 10.1287/moor.21.3.615
– ident: 572_CR10
– volume: 17
  start-page: 526
  issue: 2
  year: 2007
  ident: 572_CR18
  publication-title: SIOPT
  doi: 10.1137/050635225
SSID ssj0001388
Score 2.531066
Snippet This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale machine learning problems. The first part...
Issue Title: Special Issue on ISMP 2012 This paper presents a methodology for using varying sample sizes in batch-type optimization methods for large-scale...
SourceID proquest
pascalfrancis
crossref
springer
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 127
SubjectTerms Algorithms
Alliances
Applied sciences
Approximation
Calculus of variations and optimal control
Calculus of Variations and Optimal Control; Optimization
Combinatorics
Datasets
Exact sciences and technology
Full Length Paper
Input output
Machine learning
Mathematical analysis
Mathematical and Computational Physics
Mathematical Methods in Physics
Mathematical programming
Mathematics
Mathematics and Statistics
Mathematics of Computing
Methods
Numerical Analysis
Operational research and scientific management
Operational research. Management science
Optimization
Optimization algorithms
Sample size
Sample variance
Sampling techniques
Sciences and techniques of general use
Studies
Theoretical
Voice recognition
SummonAdditionalLinks – databaseName: SpringerLink Journals
  dbid: RSV
  link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LS8NAEB60elDEtxitZQVPSiDZbB57VLF4sYhV6S1sdjdSsGlpWg_-emfTJLaigl4CIbNLmNnHt8zs9wGcySQRWnBl-wkPbeaqyHBARjZjmiVUq4C6aSE2EXY6Ua_H78t73HlV7V6lJIuVeu6ym1uUSVIbMQaeoJZhBXe7yOg1PHSf6-XX9aKo0mk14KBKZX7XxcJmtDESOfolnQlaLCDOL0nSYu9pb_3rr7dhs4Sa5HI2NnZgSWe7sD5HQIhvdzVra74HV11huIJJ3n_HRyGQg1Ej_YwMcWEZlDc2yUx0OicId8mgqMXUpBSfeNmHp_bN4_WtXWos2NIL-cRWgZuKwFHU0Z5iNPV0IKSSLPUT4UgmDIBLvETgqZH7yvDN4QHFR5tQIzqTvncAjWyY6UMgwqMeE1SiYcJk6HCdIviiGqMdOSqMLHAqZ8eyJCA3Ohiv8Sd1snFWjM6KjbNi34Lzusloxr7xm3FrIYJ1CxpQbpjOLGhWIY3LmZrHRmYtpOZcacFp_RnnmEmciEwPp2jDOOIsRE7cgosqzPNd_PBHR3-yPoY1WowTU13YhMZkPNUnsCrfJv183CoG-QfJRPS1
  priority: 102
  providerName: Springer Nature
Title Sample size selection in optimization methods for machine learning
URI https://link.springer.com/article/10.1007/s10107-012-0572-5
https://www.proquest.com/docview/1030720144
https://www.proquest.com/docview/1494319019
Volume 134
WOSCitedRecordID wos000306493800006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVPQU
  databaseName: ABI/INFORM Collection
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: 7WY
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/abicomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ABI/INFORM Global
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: M0C
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/abiglobal
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Advanced Technologies & Aerospace Database
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: P5Z
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/hightechjournals
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Computer Science Database
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: K7-
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: http://search.proquest.com/compscijour
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Engineering Database
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: M7S
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: http://search.proquest.com
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: BENPR
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Science Database
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 20171231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: M2P
  dateStart: 20011001
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/sciencejournals
  providerName: ProQuest
– providerCode: PRVAVX
  databaseName: SpringerLink Journals
  customDbUrl:
  eissn: 1436-4646
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001388
  issn: 0025-5610
  databaseCode: RSV
  dateStart: 19970101
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7RlgOoKq8iUsrKSJxAFonjxMmpolUrJLSrVZdH4RI5toNWotml2fbAr2cmcdJuJXrhMpIV5zkT57Nn8n0Ab0xZaqdzy5MyV1xGNiMOyIxL6WQpnE1FVLViE2oyyc7O8qlfcGt8WWU_JrYDtV0YWiN_T3JYShD-P1j-5qQaRdlVL6GxAVuIbCIq6RqL6TASR3GW9ZKthBP6rGb361zUFl0KjogF52Nr36XtpW7wEVWdtsUa-LyVL20_QyeP_vcGHsOOB6DsQxcxT-Ceq5_Cwxu0hNgaD1yuzTM4nGliEGbN_A-aVjYHfcnmNVvgcHPu_-NknRR1wxAEs_O2QtMxL0nxcxe-nBx_PvrIvfICN7HKV9ymUaXT0IrQxVaKKnapNtbIKil1aKQmWFfGpca5ZJ5YYqHDaUuCfZRDzGaS-Dls1ovavQCmYxFLLQx2LKVRYe4qhGTCYQxkoVVZAGH_3AvjaclJHeNXcU2oTK4q0FUFuapIAng77LLsODnu6jxac-awh0hFTvxnAez3_ir8-9sU184K4PWwGd88Sqfo2i0usY_MEX0hnsoDeNdHxc1D_OOK9u4-4Ut4INqwpCLDfdhcXVy6V3DfXK3mzcUINtS37yPYOjyeTE-x9UlxtOPwaNSGPlk1QztNfqA9nX39C4LcBqk
linkProvider ProQuest
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V3bSt1AFN2IFbQUL7WlqbcR2hclNJlMLvMgolVR1INQC77FycykHKg5p-ZYsR_Vb3Tv3PQU6psPvgRCZnKbNTtrMnvWAviks0xZJY0bZjJ2hW8S0oBMXCGsyLg1Effzymwi7vWSiwt5NgF_27UwlFbZxsQqUJuBpn_kX8gOK-bE_7eHv1xyjaLZ1dZCo4bFsb27xSFbuXW0h-37mfOD_fOvh27jKuDqIJYj10R-riLPcM8GRvA8sJHSRos8zJSnhSLKkgWZwnGSDA0prCElD7FMbJGPaHKJwJD_SpCyGKUK8rMu8vtBkrQWscRL2lnUeqmeXyV5chcZEo7_xr6Db4aqxCbJay-NMbL7z_xs9dk7mHtpL2weZhuCzXbqHrEAE7Z4C68fyS7i3mmnVVsuwu43RQrJrOz_wU1lC4RYZf2CDTCcXjXrVFlttV0yJPnsqspAtayx3PjxDr4_yyO9h8liUNgPwFTAA6G4xoKZ0LEnbY6Uk1vEeOKZOHHAa9s51Y3sOrl__EwfBKMJGilCIyVopKEDG12VYa058lTh1THwdDV4xCXpuzmw3OIjbeJTmT6Aw4H17jBGFpouUoUd3GAZIZFdIl-UDmy2KHx8iv_c0cenL7gG04fnpyfpyVHveAlmeNUlKKFyGSZH1zd2Bab071G_vF6tOheDy-cG5z1upVxC
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1ZS8QwEB68EEW8xXpG8Ekptml65NFrUdRF8MC3kiapLGh3sasP_nonvdwVFcSXQukktJOj3zCT7wPYlUkitODK9hMe2sxVkeGAjGzGNEuoVgF100JsImy3o4cHfl3pnOZ1tXudkizPNBiWpqx_0FPpwcDBN7comaQ24g2MpkZhnJk6ehOu39w3W7HrRVGt2WqAQp3W_K6LoR_TTE_k6KO0FLcYQp9fEqbFf6g19-8vmIfZCoKSw3LOLMCIzhZheoCYEO-uGjbXfAmOboThECZ55x0vhXAOjibpZKSLG85zdZKTlGLUOUEYTJ6LGk1NKlGKx2W4a53eHp_ZlfaCLb2Q920VuKkIHEUd7SlGU08HQirJUj8RjmTCALvESwRGk9xXhocOAxcfbUKNqE363gqMZd1MrwIRHvWYoBINEyZDh-sUQRnVOAsiR4WRBU7t-FhWxORGH-Mp_qRUNs6K0VmxcVbsW7DXNOmVrBy_GW8NjWbTggaUGwY0Czbq4Y2rFZzHRn4tpCbetGCneYxrzyRURKa7r2jDOOIvRFTcgv16yAe7-OGN1v5kvQ2T1yet-PK8fbEOU7SYMqYAcQPG-i-vehMm5Fu_k79sFXP_A0M0AIw
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=proceeding&rft.title=Mathematical+programming&rft.atitle=Sample+size+selection+in+optimization+methods+for+machine+learning&rft.au=BYRD%2C+Richard+H&rft.au=CHIN%2C+Gillian+M&rft.au=NOCEDAL%2C+Jorge&rft.au=YUCHEN+WU&rft.date=2012-08-01&rft.pub=Springer&rft.issn=0025-5610&rft.volume=134&rft.issue=1&rft.spage=127&rft.epage=155&rft_id=info:doi/10.1007%2Fs10107-012-0572-5&rft.externalDBID=n%2Fa&rft.externalDocID=26294228
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0025-5610&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0025-5610&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0025-5610&client=summon