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.
and Kalai, Adam Tauman and McMahan, H
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A restarting-based nonparametric online learning method for dynamic pricing with one-point revenue feedback that achieves regret bounds scaling with time horizon and total market variation.
citing papers explorer
-
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.
-
Nonparametric Learning and Earning with One-Point Feedback under Nonstationarity
A restarting-based nonparametric online learning method for dynamic pricing with one-point revenue feedback that achieves regret bounds scaling with time horizon and total market variation.