Lipschitzian SLLNs for random functions
Abstract
We prove strong laws of large numbers for locally Lipschitz functions in the Lipschitz pseudometric. Our results hold under either a topological or a model-theoretic condition, with the latter encompassing functions jointly definable in o-minimal structures but extending substantially beyond this class. Applications include uniform convergence of limiting and Clarke subdifferentials and finite-sample identification of solutions. Consequently, we identify broad classes of functions for which the ...
Description / Details
We prove strong laws of large numbers for locally Lipschitz functions in the Lipschitz pseudometric. Our results hold under either a topological or a model-theoretic condition, with the latter encompassing functions jointly definable in o-minimal structures but extending substantially beyond this class. Applications include uniform convergence of limiting and Clarke subdifferentials and finite-sample identification of solutions. Consequently, we identify broad classes of functions for which the failure phenomena revealed by our previous negative results [Tian and Royset, arXiv:2511.16568, 2025] do not occur.
Source: arXiv:2607.20411v1 - http://arxiv.org/abs/2607.20411v1 PDF: https://arxiv.org/pdf/2607.20411v1 Original Link: http://arxiv.org/abs/2607.20411v1
Please sign in to join the discussion.
No comments yet. Be the first to share your thoughts!
Jul 23, 2026
Data Science
Machine Learning
0