Hypothesis Set Stability and Generalization

We present a study of generalization for data-dependent hypothesis sets. We give a general learning guarantee for data-dependent hypothesis sets based on a notion of transductive Rademacher complexity. Our main result is a generalization bound for data-dependent hypothesis sets expressed in terms of a notion of hypothesis set stability and a notion of Rademacher complexity for data-dependent hypothesis sets that we introduce. This bound admits as special cases both standard Rademacher complexity bounds and algorithm-dependent uniform stability bounds. We also illustrate the use of these learning bounds in the analysis of several scenarios.

Authors

• Dylan Foster MIT
• Spencer Greenberg Spark Wave
• Satyen Kale
• Haipeng Luo
• Mehryar Mohri
• Karthik Sridharan

Keywords

No keywords are indexed for this paper.