High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
Journal of Machine Learning Research , volume=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Zeroth-order SGD learning dynamics are governed by a random low-dimensional projection of the empirical NTK whose approximation error scales with model output dimension, not parameter count.
Decentralized SGD and SGDA under Markovian sampling admit non-asymptotic generalization bounds that incorporate network topology, Markov mixing rates, and primal-dual dynamics.
citing papers explorer
-
Unveiling High-Probability Generalization in Decentralized SGD
High-probability generalization bounds for D-SGD are derived at the optimal rate O(1/sqrt(mn) log(1/δ)) via pointwise uniform stability across convex and non-convex settings.
-
Learning Dynamics of Zeroth-Order Optimization: A Kernel Perspective
Zeroth-order SGD learning dynamics are governed by a random low-dimensional projection of the empirical NTK whose approximation error scales with model output dimension, not parameter count.
-
Stability and Generalization for Decentralized Markov SGD
Decentralized SGD and SGDA under Markovian sampling admit non-asymptotic generalization bounds that incorporate network topology, Markov mixing rates, and primal-dual dynamics.