Also known as covariate shift (shift between training and testing in the distribution of the input variables), see Bickel 2009.

• Bickel et al 2009 - Discriminative Learning Under Covariate Shift
• Duchi 2018 - Learning Models with Uniform Performance via Distributionally Robust Optimization
• Duchi et al 2020 - Distributionally Robust Losses for Latent Covariate Mixtures
• Zhou et al 2022 - Model Agnostic Sample Reweighting for Out-of-Distribution Learning

• Michel et al 2021 - Modeling the Second Player in Distributionally Robust Optimization
• Michel 2021 - Learning Neural Models for Natural Language Processing in the Face of Distributional Shift PhD thesis
• Michel 2022 - Distributionally Robust Models with Parametric Likelihood Ratios

• In NLP
  • Uppaal et al 2023 - Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detection

• WILDS: (paper) A benchmark of in-the-wild distribution shifts

• Paul Michel See his 2021 thesis
• Pang Wei Koh
• Percy Liang
• Tatsunori Hashimoto

• Fairness (Methods that are not robust to distribution shift may not be fair across populations)
• Robustness in NLP