CMSC Spring Learning Theory Lecture Mistake Bound Model Halving Algorithm Linear Classiers Instructors Sham Kakade and Ambuj Tewari Introduction This course will be divided into parts - PDF document

Download presentation
CMSC  Spring  Learning Theory Lecture  Mistake Bound Model Halving Algorithm Linear Classiers Instructors Sham Kakade and Ambuj Tewari  Introduction This course will be divided into  parts
CMSC  Spring  Learning Theory Lecture  Mistake Bound Model Halving Algorithm Linear Classiers Instructors Sham Kakade and Ambuj Tewari  Introduction This course will be divided into  parts

CMSC Spring Learning Theory Lecture Mistake Bound Model Halving Algorithm Linear Classiers Instructors Sham Kakade and Ambuj Tewari Introduction This course will be divided into parts - Description


In each part we will make different assumptions about the data generating process Online Learning No assumptions about data generating process Worst case analysis Fundamental connections to Game Theory Statistical Learning Assume data consists of in ID: 6971 Download Pdf

Tags

each part

Embed / Share - CMSC Spring Learning Theory Lecture Mistake Bound Model Halving Algorithm Linear Classiers Instructors Sham Kakade and Ambuj Tewari Introduction This course will be divided into parts


Presentation on theme: "CMSC Spring Learning Theory Lecture Mistake Bound Model Halving Algorithm Linear Classiers Instructors Sham Kakade and Ambuj Tewari Introduction This course will be divided into parts"— Presentation transcript


Notethatweareignoringefciencyissueshere.WehavenotsaidanythingabouttheamountofcomputationAhastodoineachroundinordertoupdateitshypothesisfromhttoht+1.Settingthisissueasideforamoment,wehavearemarkablysimplealgorithmHALVING(C)thathasamistakeboundoflg(jCj)foranyniteconceptclassC.ForanitesetHofhypotheses,denethehypothesismajority(H)asfollows,majority(H)(x):=(+1jfh2Hjh(x)=+1gjjHj=2;�1otherwise: Algorithm1HALVING(C) C1 Ch1 majority(C1)fort=1toTdoReceivextPredictht(xt)ReceiveytCt+1 ff2Ctjf(xt)=ytght+1 majority(Ct+1)endfor Theorem2.2.ForanyniteconceptclassC,wehavemistake(HALVING(C);C))lgjCj:Proof.ThekeyideaisthatifthealgorithmmakesamistakethenatleasthalfofthehypothesisinCtareeliminated.Formally,ht(xt)6=yt)jCt+1jjCtj=2:Therefore,denotingthenumberofmistakesuptotimetbyMt,Mt:=TXt=11[ht(xt)6=yt];wehavejCt+1jjC1j 2Mt=jCj 2Mt(1)Sincethereisanf2Cwhichperfectlyclassiesallxt,wealsohave1jCt+1j:(2)Combining(1)and(2),wehave1jCj 2Mt;whichgivesMtlg(jCj). 3LinearClassiersandMarginLetusnowlookataconcreteexampleofaconceptclass.SupposeX=Rdandwehaveavectorw2Rd.Wedenethehypothesis,hw(x)=sgn(wx);2 Thisboundisnicebecauseeventhoughwehadanuncountableconceptclasstobeginwith,themarginassumptionallowedustoworkwithanitesubsetoftheconceptclassandwewereabletoderiveamistakebound.However,theresultisunsatisfactorybecauserunningthehalvingalgorithmonC linisextremelyinefcient.Onemightwonderifonecanusethespecialstructureofthespaceoflinearclassierstoimplementthehalvingalgorithmmoreefciently.Indeed,itpossibletoimplementavariantofthehalvingalgorithmefcientlyusingtheellipsoidmethoddevelopedforthelinearprogrammingfeasibilityproblem.Notethatthemistakebounddependsexplicitlyonthedimensiondoftheproblem.Wewouldalsoliketobeabletogiveadimensionindependentmistakebound.Indeed,aclassicalgorithmcalledPERCEPTRONhassuchamistakebound.4

Shom More....
By: marina-yarberry
Views: 148
Type: Public

Download Section

Please download the presentation after appearing the download area.


Download Pdf - The PPT/PDF document "CMSC Spring Learning Theory Lecture M..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Try DocSlides online tool for compressing your PDF Files Try Now

Related Documents