Decontamination of Mutual Contamination Models
arXiv:1710.01167
Abstract
Many machine learning problems can be characterized by mutual contamination models. In these problems, one observes several random samples from different convex combinations of a set of unknown base distributions and the goal is to infer these base distributions. This paper considers the general setting where the base distributions are defined on arbitrary probability spaces. We examine three popular machine learning problems that arise in this general setting: multiclass classification with label noise, demixing of mixed membership models, and classification with partial labels. In each case, we give sufficient conditions for identifiability and present algorithms for the infinite and finite sample settings, with associated performance guarantees.
arXiv commentPublished in JMLR. Subsumes arXiv:1602.06235
References in corpus (6)
- Robust Loss Functions under Label Noise for Deep Neural Networks
- On the Topic of Jets: Disentangling Quarks and Gluons at Colliders
- Mixture Proportion Estimation via Kernel Embedding of Distributions
- Topic Discovery through Data Dependent and Random Projections
- Nonparametric semi-supervised learning of class proportions
- Learning in the Presence of Corruption