Answers are grounded in this paper and cite their sources.
In this paper, we study stochastic gradient descent in the smooth interpolation regime, where the population objective shares a common minimizer with the sample losses. In contrast to prior work, which has largely focused on in-expectation analysis, we obtain high-probability convergence guarantees under the same assumptions. In the convex case, we prove a fast rate of order log(β⁻¹) · n⁻¹ after n iterations, with failure probability at most $β$. In the strongly convex case, we derive a family of moment-based bounds of order β⁻ᵖ · exp(-O(p · n)) for p ∈ (0,1], and complement them with a matching lower bound showing that the corresponding deterioration in the exponential rate is essentially unavoidable. In both settings, our theoretical results are unified across a broad class of step-size schedules. Building on this analysis, we extend our results to a low-noise regime and to nonconvex objectives satisfying the Polyak-Lojasiewicz condition.
No takes yet. Share an insight, caveat, or question.
Galli et al. (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: