deep gamblers: learning to abstain with portfolio...
TRANSCRIPT
![Page 1: Deep Gamblers: Learning to Abstain with Portfolio Theorypliang/posters/neurips2019_gamblers_poster.pdf · zuwmžz 100 90 80 70 60 50 40 30 20 20 2.0 acc gblers loss gblers acc nll](https://reader036.vdocuments.net/reader036/viewer/2022062603/5f6ea8f32ceb9f45527af614/html5/thumbnails/1.jpg)
DeepGamblers:LearningtoAbstainwithPortfolioTheoryLiuZiyin(U.Tokyo),ZhikangT.Wang(U.Tokyo),PaulPuLiang(CMU),
RuslanSalakhutdinov(CMU),Louis-PhilippeMorency(CMU),MasahitoUeda(U.Tokyo)
ClassificationandtheInadequacyof𝒏𝒍𝒍 lossWanttofind:𝜃 = argmax
*Pr(𝑌|𝜃)
Inpractice,minimize𝑛𝑒𝑔𝑎𝑡𝑖𝑣𝑒𝑙𝑜𝑔𝑙𝑜𝑠𝑠 (𝑛𝑙𝑙 loss):min*− log 𝑝(𝑌|𝜃)
ProposedMethod:TheGambler’sLoss
max𝐸 log 𝑆 = maxC𝑝D
E
DFG
log(𝑜D𝑏D + 𝑏J)
SOTAPerformanceonSelectiveClassification
SurprisingBenefit-Trainingwithgambler’slossreducesoverfitting-Improvedperformancewhennoisylabelsarepresent
TheLearnedRepresentationisBetterSeparable
ToyExample:ImageRotation
Intuition:PredictionasHorseRaceHorseRacewithReservation
𝑚 horsesBettingstrategy:∑ 𝑏DM
DFG → ∑ 𝑏DEDFJ
Chanceofwinning:𝑝DPayoffifwebetonthewinninghorse:𝑜DReturnafterwinning:𝑆 = 𝑜D𝑏D → 𝑜D𝑏D + 𝑏J
Objective:maximizedoublingrate:
max𝑊 = max𝐸 log 𝑆 = maxC𝑝D
E
DFG
log(𝑜D𝑏D + 𝑏J)
-ClassificationProblem= BettingproblemwithReservationwith𝑜 = 1, 𝑏J = 0-ClassificationProblem≤ BettingproblemwithReservation
ToyExample:IdentifyingDisconfidentImagesPaper:
Code: