Limits of Algorithmic Stability for Distributional Generalization

Neha Hulkund, Vinith Menon Suriyakumar, Taylor W. Killian, Marzyeh Ghassemi

Keywords: Distribution Shift, Robustness, Evaluation

TL;DR: In this paper we empirically show that the more stable a learning algorithm is the more robust the resulting model is to covariate, label, and subpopulation shifts.

Abstract: As machine learning models become widely considered in safety critical settings, it is important to understand when models may fail after deployment. One cause of model failure is distribution shift, where the training and test data distributions differ. In this paper we investigate the benefits of training models using methods which are algorithmically stable towards improving model robustness, motivated by recent theoretical developments which show a connection between the two. We use techniques from differentially private stochastic gradient descent (DP-SGD) to control the level of algorithmic stability during training. We compare the performance of algorithmically stable training procedures to stochastic gradient descent (SGD) across a variety of possible distribution shifts - specifically covariate, label, and subpopulation shifts. We find that models trained with algorithmically stable procedures result in models with consistently lower generalization gap across various types of shifts and shift severities. as well as a higher absolute test performance in label shift. Finally, we demonstrate that there is there is a tradeoff between distributional robustness, stability, and performance.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)