Disambiguation of weak supervision with exponential convergence rates
arXiv:2102.02789
Abstract
Machine learning approached through supervised learning requires expensive annotation of data. This motivates weakly supervised learning, where data are annotated with incomplete yet discriminative information. In this paper, we focus on partial labelling, an instance of weak supervision where, from a given input, we are given a set of potential targets. We review a disambiguation principle to recover full supervision from weak supervision, and propose an empirical disambiguation algorithm. We prove exponential convergence rates of our algorithm under classical learnability assumptions, and we illustrate the usefulness of our method on practical examples.
arXiv comment22 pages; 6 figures
References in corpus (8)
- HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
- Fast learning rates for plug-in classifiers
- Generalization error bounds in semi-supervised classification under the cluster assumption
- Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data
- Missing Data Imputation using Optimal Transport
- A Consistent Regularization Approach for Structured Prediction
- A Structured Prediction Approach for Label Ranking
- Sharp Analysis of Learning with Discrete Losses