Online Adaptation to Label Distribution Shift
arXiv:2107.04520
Abstract
Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting, where the test-time label distribution is continually changing and the model must dynamically adapt to it without observing the true label. Leveraging a novel analysis, we show that the lack of true label does not hinder estimation of the expected test loss, which enables the reduction of online label shift adaptation to conventional online learning. Informed by this observation, we propose adaptation algorithms inspired by classical online learning techniques such as Follow The Leader (FTL) and Online Gradient Descent (OGD) and derive their regret bounds. We empirically verify our findings under both simulated and real world label distribution shifts and show that OGD is particularly effective and robust to a variety of challenging label shift scenarios.
References in corpus (8)
- On Calibration of Modern Neural Networks
- Domain Adaptation: Learning Bounds and Algorithms
- Beyond Sharing Weights for Deep Domain Adaptation
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- Wasserstein Distance Guided Representation Learning for Domain Adaptation
- On Causal and Anticausal Learning
- Regularized Learning for Domain Adaptation under Label Shifts
- A Unified View of Label Shift Estimation