Mixture Proportion Estimation Beyond Irreducibility

The task of mixture proportion estimation (MPE) is to estimate the weight of a component distribution in a mixture, given observations from both the component and mixture. Previous work on MPE adopts the irreducibility assumption, which ensures identifiablity of the mixture proportion. In this paper, we propose a more general sufficient condition that accommodates several settings of interest where irreducibility does not hold. We further present a resampling-based meta-algorithm that takes any existing MPE algorithm designed to work under irreducibility and adapts it to work under our more general condition. Our approach empirically exhibits improved estimation performance relative to baseline methods and to a recently proposed regrouping-based algorithm.

[1]  Yuekai Sun,et al.  A linear adjustment-based approach to posterior drift in transfer learning. , 2021, Biometrika.

[2]  Jian Yang,et al.  Instance-Dependent Positive and Unlabeled Learning With Labeling Bias Estimation , 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Masashi Sugiyama,et al.  Rethinking Class-Prior Estimation for Positive-Unlabeled Learning , 2020, ICLR.

[4]  Sivaraman Balakrishnan,et al.  Mixture Proportion Estimation and PU Learning: A Modern Approach , 2021, NeurIPS.

[5]  E. Pierson,et al.  Quantifying Inequality in Underreported Medical Conditions , 2021, ArXiv.

[6]  T. Tony Cai,et al.  Transfer Learning for Nonparametric Classification: Minimax Rate and Adaptive Classifier , 2019, The Annals of Statistics.

[7]  Dmitry Ivanov.  DEDPUL: Difference-of-Estimated-Densities-based Positive-Unlabeled Learning , 2019, 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA).

[8]  Jesse Davis,et al.  Learning from positive and unlabeled data: a survey , 2018, Machine Learning.

[9]  Bo Hu,et al.  Review of recent gamma spectrum unfolding algorithms and their application , 2019, Results in Physics.

[10]  Clayton Scott,et al.  A Generalized Neyman-Pearson Criterion for Optimal Domain Adaptation , 2018, ALT.

[11]  Masahiro Kato,et al.  Learning from Positive and Unlabeled Data with a Selection Bias , 2018, ICLR.

[12]  Jesse Davis,et al.  Beyond the Selected Completely At Random Assumption for Learning from Positive and Unlabeled Data , 2018, ECML/PKDD.

[13]  Jesse Davis,et al.  Estimating the Class Prior in Positive and Unlabeled Data Through Decision Tree Induction , 2018, AAAI.

[14]  Gang Niu,et al.  Positive-Unlabeled Learning with Non-Negative Risk Estimator , 2017, NIPS.

[15]  Ambuj Tewari,et al.  Mixture Proportion Estimation via Kernel Embeddings of Distributions , 2016, ICML.

[16]  Martha White,et al.  Nonparametric semi-supervised learning of class proportions , 2016, ArXiv.

[17]  Clayton Scott,et al.  A Rate of Convergence for Mixture Proportion Estimation, with Application to Learning from Noisy Labels , 2015, AISTATS.

[18]  Gang Niu,et al.  Analysis of Learning from Positive and Unlabeled Data , 2014, NIPS.

[19]  Masashi Sugiyama,et al.  Class Prior Estimation from Positive and Unlabeled Data , 2014, IEICE Trans. Inf. Syst..

[20]  Clayton Scott,et al.  Class Proportion Estimation with Application to Multiclass Anomaly Rejection , 2013, AISTATS.

[21]  Nagarajan Natarajan,et al.  Learning with Noisy Labels , 2013, NIPS.

[22]  Bernhard Schölkopf,et al.  Domain Adaptation under Target and Conditional Shift , 2013, ICML.

[23]  Gilles Blanchard,et al.  Semi-Supervised Novelty Detection , 2010, J. Mach. Learn. Res..

[24]  Steffen Bickel,et al.  Discriminative Learning Under Covariate Shift , 2009, J. Mach. Learn. Res..

[25]  Karsten M. Borgwardt,et al.  Covariate Shift by Kernel Mean Matching , 2009, NIPS 2009.

[26]  Neil D. Lawrence,et al.  When Training and Test Sets Are Different: Characterizing Learning Transfer , 2009 .

[27]  M. Tremblay,et al.  The accuracy of self-reported smoking: a systematic review of the relationship between self-reported and cotinine-assessed smoking status. , 2009, Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco.

[28]  Charles Elkan,et al.  Learning classifiers from only positive and unlabeled data , 2008, KDD.

[29]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[30]  Marco Saerens,et al.  Adjusting the Outputs of a Classifier to New a Priori Probabilities: A Simple Procedure , 2002, Neural Computation.

[31]  Bernhard Schölkopf,et al.  Estimating a Kernel Fisher Discriminant in the Presence of Label Noise , 2001, ICML.

[32]  Qi Zhang,et al.  EM-DD: An Improved Multiple-Instance Learning Technique , 2001, NIPS.

[33]  W. Jason Owen,et al.  Statistical Data Analysis , 2000, Technometrics.

[34]  H.W. Kraner,et al.  Radiation detection and measurement , 1981, Proceedings of the IEEE.

[35]  J. Heckman.  Sample selection bias as a specification error , 1979 .