2021/03/05 by Kilian Fatras, Fatras, Kilian, Thibault Séjourné +5 · 10 citations
Computer Science · Engineering · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #FOS: Mathematics #Infrastructure Maintenance and Monitoring #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and ELM #Statistics Theory (math.ST)
paper · pdf · doi:10.48550/arxiv.2103.03606
openalex publication_date 2021/03/05 · openalex created_date 2021/03/15 · openalex updated_date 2026/07/28
Optimal transport distances have found many applications in machine learning for their capacity to compare non-parametric probability distributions. Yet their algorithmic complexity generally prevents their direct use on large scale datasets. Among the possible strategies to alleviate this issue, practitioners can rely on computing estimates of these distances over subsets of data, \em i.e. minibatches. While computationally appealing, we highlight in this paper some limits of this strategy, arguing it can lead to undesirable smoothing effects. As an alternative, we suggest that the same minibatch strategy coupled with unbalanced optimal transport can yield more robust behavior. We discuss the associated theoretical properties, such as unbiased estimators, existence of gradients and concentration bounds. Our experimental study shows that in challenging problems associated to domain adaptation, the use of unbalanced optimal transport leads to significantly better results, competing with or surpassing recent baselines.