Develops sharp concentration inequalities under finite Lp moments extending McDiarmid's bounded differences, then derives high-probability generalization bounds for ERM, transductive regression, and meta-learning under Lp stability.
Convergence of first-order algorithms for meta-learning with moreau envelopes.arXiv preprint arXiv:2301.06806
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A trust-region stabilized proximal point method enforces a displacement condition to achieve linear descent for general nonsmooth convex problems.
citing papers explorer
-
Stability beyond Bounded Differences: Sharp Generalization Bounds under Finite $L_p$ Moments
Develops sharp concentration inequalities under finite Lp moments extending McDiarmid's bounded differences, then derives high-probability generalization bounds for ERM, transductive regression, and meta-learning under Lp stability.
-
Stabilized Proximal Point Method via Trust Region Control
A trust-region stabilized proximal point method enforces a displacement condition to achieve linear descent for general nonsmooth convex problems.