A Survey on Scenario Theory, Complexity, and Compression-Based Learning and Generalization

This work investigates formal generalization error bounds that apply to support vector machines (SVMs) in realizable and agnostic learning problems. We focus on recently observed parallels between probably approximately correct (PAC)-learning bounds, such as compression and complexity-based bounds, and novel error guarantees derived within scenario theory. Scenario theory provides nonasymptotic and distributional-free error bounds for models trained by solving data-driven decision-making problems. Relevant theorems and assumptions are reviewed and discussed. We propose a numerical comparison of the tightness and effectiveness of theoretical error bounds for support vector classifiers trained on several randomized experiments from 13 real-life problems. This analysis allows for a fair comparison of different approaches from both conceptual and experimental standpoints. Based on the numerical results, we argue that the error guarantees derived from scenario theory are often tighter for realizable problems and always yield informative results, i.e., probability bounds tighter than a vacuous $[0,1]$ interval. This work promotes scenario theory as an alternative tool for model selection, structural-risk minimization, and generalization error analysis of SVMs. In this way, we hope to bring the communities of scenario and statistical learning theory closer, so that they can benefit from each other's insights.

Automated summary

This work investigates formal generalization error bounds for support vector machines (SVMs) in realizable and agnostic learning problems. It focuses on the parallels between probably approximately correct (PAC)-learning bounds and novel error guarantees derived within scenario theory. The numerical comparison of different error bounds for SVMs trained on real-life problems suggests that scenario theory provides tighter and more informative results compared to other approaches.