The interplay of robustness and generalization in quantum machine learning
This work addresses the combined robustness and generalization problem for quantum machine learning practitioners, but it appears incremental as it builds on existing Lipschitz bound methods.
The paper tackles the interplay between adversarial robustness and generalization in variational quantum models, showing that both can be quantified via Lipschitz bounds to enable a regularization-based training approach, with practical implications demonstrated in time series analysis.
While adversarial robustness and generalization have individually received substantial attention in the recent literature on quantum machine learning, their interplay is much less explored. In this chapter, we address this interplay for variational quantum models, which were recently proposed as function approximators in supervised learning. We discuss recent results quantifying both robustness and generalization via Lipschitz bounds, which explicitly depend on model parameters. Thus, they give rise to a regularization-based training approach for robust and generalizable quantum models, highlighting the importance of trainable data encoding strategies. The practical implications of the theoretical results are demonstrated with an application to time series analysis.