# Reproduction: Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite Lp Moments

ICML 2026 · OpenReview SGTLVjx3MN · arXiv 2606.06855 · CPU-only local reproduction.

| Page | slug |
|---|---|
| Executive summary | executive-summary |
| Theorem 2.2 establishes a concentration inequality for functions of in… | claim-1-theorem-2-2-two-regime-concentration |
| Theorem 2.6 extends the concentration results to the heavy-tailed regi… | claim-2-theorem-2-6-heavy-tailed-regime |
| Assumption 3.1 defines (Lp,β)-Lipschitz stability, requiring only that… | claim-3-assumption-3-1-lp-lipschitz-stability |
| Theorem 3.4 provides a high-probability generalization bound for empir… | claim-4-theorem-3-4-erm-generalization |
| Theorems 3.9 and 3.10 extend the concentration framework to sampling w… | claim-5-theorems-3-9-3-10-transductive |
| Theorem 3.14 establishes high-probability generalization bounds for me… | claim-6-theorem-3-14-meta-learning |
| Conclusion | conclusion |