Lock in $30 Savings on PRO—Offer Ends Soon! ⏳

CW, AROW, and SCW

CW, AROW, and SCW

Confidence-weighted Algorithm (CW), Adaptive Regularization of Weight Vectors (AROW), and Exact Soft Confidence-Weighted Learning (SCW).

Sorami Hisamoto

May 27, 2014
Tweet

More Decks by Sorami Hisamoto

Other Decks in Research

Transcript

  1. 7BSJPVTPOMJOFMFBSOJOHBMHPSJUINT ‣ 1FSDFQUSPO<3PTFOCMBUU> ‣ \.BSHJO 7PUFE "WFSBHFE 4FDPOEPSEFS 4USVDUVSFE ʜ^1FSDFQUSPO

    ‣ .*3"1".BSHJO*OGVTFE3FMBYFE"MHPSJUIN1BTTJWF"HHSFTTJWF<$SBNNFS > ‣ $8$POpEFODF8FJHIUFE"MHPSJUIN<%SFE[F > ‣ *&--*1*NQSPWFE&MMJQTPJE.FUIPE<:BOH > ‣ "308"EBQUJWF3FHVMBSJ[BUJPOPG8FJHIU7FDUPST<$SBNNFS > ‣ /"308/FX"EBQUJWF"MHPSJUINTGPS0OMJOF$MBTTJpDBUJPO<0SBCPOB$SBNNFS> ‣ /)&3%/PSNBM)FSE<$SBNNFS > ‣ "EB(SBE"EBQUJWF4VC(SBEJFOU.FUIPET<%VDIJ > ‣ 4$8&YBDU4PGU$POpEFODF8FJHIUFE-FBSOJOH<8BOH > ‣ ʜ 2
  2. 1"1BTTJWF"HHSFTTJWFBMHPSJUIN<$SBNNFS > 3 minimally update ‣ *GSFTVMUDPSSFDU EPOPUIJOH QBTTJWF 

    ‣ *GSFTVMUXSPOH NJOJNBMMZVQEBUFXFJHIUTUPDMBTTJGZDPSSFDUMZ BHHSFTTJWF 
  3. 1"1BTTJWF"HHSFTTJWFBMHPSJUIN<$SBNNFS > 3 minimally update ‣ *GSFTVMUDPSSFDU EPOPUIJOH QBTTJWF 

    ‣ *GSFTVMUXSPOH NJOJNBMMZVQEBUFXFJHIUTUPDMBTTJGZDPSSFDUMZ BHHSFTTJWF  correctly classify
  4. 1"1BTTJWF"HHSFTTJWFBMHPSJUIN<$SBNNFS > ‣ )BTDMPTFEGPSNTPMVUJPO 3 minimally update ‣ *GSFTVMUDPSSFDU EPOPUIJOH

    QBTTJWF  ‣ *GSFTVMUXSPOH NJOJNBMMZVQEBUFXFJHIUTUPDMBTTJGZDPSSFDUMZ BHHSFTTJWF  correctly classify
  5. *OTJEF$8 ‣ *OTUFBEPGXFJHIUX VTFЖ NFBOWFDUPS BOEЄ DPWBSJBODFNBUSJY  8 It

    has closed form solution (c.f. [Dredze+ 2008]). Often use diag only instead of Σ" to make it simpler (not much performance change).
  6. *OTJEF$8 ‣ *OTUFBEPGXFJHIUX VTFЖ NFBOWFDUPS BOEЄ DPWBSJBODFNBUSJY  8 Minimally

    update It has closed form solution (c.f. [Dredze+ 2008]). Often use diag only instead of Σ" to make it simpler (not much performance change).
  7. *OTJEF$8 ‣ *OTUFBEPGXFJHIUX VTFЖ NFBOWFDUPS BOEЄ DPWBSJBODFNBUSJY  8 Minimally

    update Correctly classify with 
 prob >= η It has closed form solution (c.f. [Dredze+ 2008]). Often use diag only instead of Σ" to make it simpler (not much performance change).
  8. *OTJEF"308 12 Values of hyper-parameter λ’s not so important (e.g.

    0.1). It has closed form solution (c.f. [Crammer+ 2009]).
  9. *OTJEF"308 12 Minimally update Values of hyper-parameter λ’s not so

    important (e.g. 0.1). It has closed form solution (c.f. [Crammer+ 2009]).
  10. *OTJEF"308 12 Minimally update Minimize loss Values of hyper-parameter λ’s

    not so important (e.g. 0.1). It has closed form solution (c.f. [Crammer+ 2009]).
  11. *OTJEF"308 12 Minimally update Minimize loss More data, 
 more

    confident Values of hyper-parameter λ’s not so important (e.g. 0.1). It has closed form solution (c.f. [Crammer+ 2009]).
  12. *OTJEF4$8 15 They have closed form solutions (c.f. [Wang+ 2012]).

    Formulas from d.hatena.ne.jp/kisa12012/20120625/
  13. *OTJEF4$8 15 They have closed form solutions (c.f. [Wang+ 2012]).

    Formulas from d.hatena.ne.jp/kisa12012/20120625/
  14. &WBMVBUJPO 18 ‣ .BSHJOCBTFEVTVBMMZPVUQFSGPSNTOPONBSHJOCBTFE ‎ -BSHFNBSHJO ‣ 4FDPOEPSEFSVTVBMMZPVUQFSGPSNTpSTUPSEFS ‎ $POpEFODFXFJHIUJOH

    ‣ $8PVUQFSGPSNTpSTUPSEFS CVUOPUXJUISFBMXPSME OPJTZ EBUB ‎ )BOEMJOHOPOTFQBSBCMFEBUB ‣ "308PVUQFSGPSNT$8XJUINBOZSFBMXPSMEEBUB CVUNPSFVQEBUFT ‎ "EBQUJWFNBSHJO Experiments on [Wang+ 2012]: various classification tasks.
  15. 4VNNBSZ ‣ $8DPOTJEFSDPOpEFODFPGXFJHIUT5PPBHHSFTTJWF XFBLUPOPJTF ‣ "308 4$8TPGUFOUIFDPOTUSBJOUPG$8 ‣ "3084$8DPNQBSBCMFQFSGPSNBODF ‣

    4$8JGZPVEPO`UNJOEpOEJOHPQUJNBMIZQFSQBSBNFUFSTʜ  ‣ "308PUIFSXJTFʜ 19 … but it all depends on the data sets!
  16. 1BQFST ‣ <3PTFOCMBUU>5IFQFSDFQUSPO"QSPCBCJMJTUJDNPEFMGPSJOGPSNBUJPOTUPSBHFBOEPSHBOJ[BUJPOJOUIFCSBJO ‣ <$PMMJOT>%JTDSJNJOBUJWF5SBJOJOH.FUIPETGPS)JEEFO.BSLPW.PEFMT5IFPSZBOE&YQFSJNFOUTXJUI1FSDFQUSPO"MHPSJUINT &./-1  ‣ <$FTB#JBODIJ >"TFDPOEPSEFSQFSDFQUSPOBMHPSJUIN

    4*$0.1  ‣ <$SBNNFS >0OMJOFQBTTJWFBHHSFTTJWFBMHPSJUINT +.-3  ‣ <%SFE[F >$POpEFODF8FJHIUFE-JOFBS$MBTTJpDBUJPO *$.-  ‣ <$SBNNFS >.VMUJ$MBTT$POpEFODF8FJHIUFE"MHPSJUINT &./-1  ‣ <:BOH >0OMJOFMFBSOJOHCZFMMJQTPJENFUIPE *$.-  ‣ <$SBNNFS >"EBQUJWF3FHVMBSJ[BUJPOPG8FJHIU7FDUPST /*14  ‣ <0SBCPOB$SBNNFS>/FX"EBQUJWF"MHPSJUINTGPS0OMJOF$MBTTJpDBUJPO /*14  ‣ <$SBNNFS >-FBSOJOHWJB(BVTTJBO)FSEJOH /*14  ‣ <%VDIJ >"EBQUJWF4VCHSBEJFOU.FUIPETGPS0OMJOF-FBSOJOHBOE4UPDIBTUJD0QUJNJ[BUJPO +.-3  ‣ <$SBNNFS >$POpEFODF8FJHIUFE-JOFBS$MBTTJpDBUJPOGPS5FYU$BUFHPSJ[BUJPO +-.3  ‣ <8BOH >&YBDU4PGU$POpEFODF8FJHIUFE-FBSOJOH *$.-  ‣ <)PJ >-*#0-"-JCSBSZGPS0OMJOF-FBSOJOH"MHPSJUINT +-.3 21
  17. 1SFTFOUBUJPOT ‣ l4FDPOE0SEFS-FBSOJOHz5VUPSJBM!&$.-1,%%,PCZ$SBNNFS
 IUUQXXXFDNMQLEEPSHUVUPSJBMT ‣ 0OMJOF-JOFBS$MBTTJpFSTd1FSDFQUSPO͔Β$8·Ͱdେؠल࿨
 IUUQXXXTMJEFTIBSFOFULJTBPOMJOFDMBTTJpFST ‣ "EBQUJWF3FHVMBSJ[BUJPOPG8FJHIU7FDUPSTେؠल࿨
 IUUQXXXSEMJUDVUPLZPBDKQdPJXBVQMPBE"308QEG

    ‣ େن໛σʔλΛجʹͨࣗ͠વݴޠॲཧ!4*('1"*Ԭ໺ݪେี
 IUUQTTJUFTHPPHMFDPNTJUFEBJTVLFPLBOPIBSB ‣ ΦϯϥΠϯತ࠷దԽͱઢܗࣝผϞσϧֶशͷ࠷લઢ@*#*4Ԭ໺ݪେี
 IUUQXXXTMJEFTIBSFOFUQpJCJTPLBOPIBSB ‣ 5PLZP/-1ύʔηϓτϩϯͰָ͍͠஥͕ؒΆΆΆΆʙΜ਺ݪྑ඙
 IUUQXXXTMJEFTIBSFOFUTMFFQZ@ZPTIJUPLZPOMQ ‣ 1'*$ISJTUNBTTFNJOBS
 IUUQXXXTMJEFTIBSFOFUQpQpDISJTUNBTTFNJOBS ‣ 4FDPOE0SEFS1FSDFQUSPO.JDIBFM3-ZV
 IUUQXXXDTFDVILFEVILMZV@NFEJBHSPVQNFFUJOHIRZBOH@TFDPOEPSEFSQEG ‣ "3088JMMFN,SBZFOIP⒎
 IUUQTXXXZPVUVCFDPNXBUDI W"0C@WGO1HD ‣ ύʔηϓτϩϯΞϧΰϦζϜ(SBIBN/FVCJH
 IUUQXXXQIPOUSPODPNTMJEFTOMQQSPHSBNNJOHKBQFSDFQUSPOQEG 22
  18. "SUJDMFT ‣ $POpEFODF8FJHIUFE-JOFBS$MBTTJpDBUJPOΛಡΜࣹܸͩͭͭ͠લస
 IUUQEIBUFOBOFKQULOH ‣ "308ͷίʔυΛॻ͍ͯΈͨUTVCPTBLBͷ೔ه
 IUUQEIBUFOBOFKQUTVCPTBLB ‣ "308Λ3VCZͰ࣮૷ͯ͠ΈͨdCMPHLJCJ[
 IUUQCMPHLJCJ[BSPXSVCZIUNM

    ‣ &YBDU4PGU$POpEFODF8FJHIUFE-FBSOJOH *$.- ಡΜͩLJTBͷ೔ه
 IUUQEIBUFOBOFKQLJTB ‣ ΦϯϥΠϯઢܗ෼ྨثͱ4$84JEFTXJQF
 IUUQLB[PPIBUFOBCMPHDPNFOUSZ ‣ "308͸$8ΑΓز෼Ϛγ͔OZͷ೔ه
 IUUQEIBUFOBOFKQOZQ ‣ l.*3" .BSHJO*OGVTFE3FMBYFE"MHPSJUIN zதᖒහ໌
 IUUQOMQJTUJLZPUPVBDKQNFNCFSOBLB[BXBQVCECPUIFS.*3"QEG ‣ ػցֶश௒ೖ໳**ʙ(NBJMͷ༏ઌτϨΠͰ΋࢖͍ͬͯΔ1"๏Λ෼Ͱशಘ͠Α͏ʂʙ&DIJ[FO#MPH;XFJ
 IUUQEIBUFOBOFKQFDIJ[FO@UN ‣ 5IFTJNJMBSJUZCFUXFFODPOpEFODFXFJHIUFEMFBSOJOHBOEUIFOBUVSBMHSBEJFOU"MFYBOESF1BTTPTT.-CMPH
 IUUQBUQBTTPTNFQPTUUIFTJNJMBSJUZCFUXFFODPOpEFODFXFJHIUFEMF ‣ OBUVSBMMBOHVBHFQSPDFTTJOHCMPH$MBTTJpFSQFSGPSNBODFBMUFSOBUJWFNFUSJDTPGTVDDFTT
 IUUQOMQFSTCMPHTQPUKQDMBTTJpFSQFSGPSNBODFBMUFSOBUJWFIUNM 23
  19. *NQMFNFOUBUJPOT ‣ -*#0-
 "-JCSBSZGPS0OMJOF-FBSOJOH"MHPSJUINT
 IUUQXXXDBJTOUVFEVTHdDIIPJMJCPM ‣ +VCBUVT
 %JTUSJCVUFE0OMJOF.BDIJOF-FBSOJOH'SBNFXPSL
 IUUQKVCBUVT ‣

    "308 
 "OJNQMFNFOUBUJPOPGUIFF⒏DJFOUDPOpEFODFXFJHIUFEDMBTTJpFS
 IUUQTDPEFHPPHMFDPNQBSPXQQ ‣ PMM
 0OMJOF-FBSOJOH-JCSBSZ
 IUUQTDPEFHPPHMFDPNQPMMXJLJ0MM.BJO+B 24