Contrastive learning of strong-mixing continuous-time stochastic processes

Abstract

Contrastive learning is a family of self-supervised methods where a model is trained to solve a classification task constructed from unlabeled data. It has recently emerged as one of the leading learning paradigms in the absence of labels across many different domains (e.g. brain imaging, text, images). However, theoretical understanding of many aspects of training, both statistical and algorithmic, remain fairly elusive. In this work, we study the setting of time series -- more precisely, when we get data from a strong-mixing continuous-time stochastic process. We show that a properly constructed contrastive learning task can be used to estimate the transition kernel for small-to-mid-range intervals in the diffusion case. Moreover, we give sample complexity bounds for solving this task and quantitatively characterize what the value of the contrastive loss implies for distributional closeness of the learned kernel. As a byproduct, we illuminate the appropriate settings for the contrastive distribution, as well as other hyperparameters in this setup.

arXiv commentAppearing in AISTATS 2021

References in corpus (6)

• A Simple Framework for Contrastive Learning of Visual Representations
• What Makes for Good Views for Contrastive Learning?
• A Theoretical Analysis of Contrastive Unsupervised Representation Learning
• Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases
• Contrastive estimation reveals topic posterior information to linear models