AI TrackerFrontier desk · AEST
Back to news
normalaitech

Near-Optimal Second-Order Convex Finite-Sum Optimization under Individual Smoothness

arXiv cs.AI · 31 Oct 2026, 03:04 AEST

The paper discusses advancements in stochastic second-order oracle complexity for smooth convex finite-sum optimization. It presents a new method that achieves better complexity under individual smoothness and convexity assumptions.

Key facts

Read aloud

The paper discusses advancements in stochastic second-order oracle complexity for smooth convex finite-sum optimization. It presents a new method that achieves better complexity under individual smoothness and convexity assumptions. We study the stochastic second-order oracle complexity of solving smooth convex finite-sum optimization with $n$ components. In this paper, we show that individual smoothness and convexity provably enable further acceleration, where the lower complexity bound is $Ω n+ n^ five/seven ε^ -two/seven $ under this stronger assumption. Then, by establishing a novel second-order self-bounding inequality, we design a new Taylor-corrected lazy Newton method, which can lead to a better complexity of $\tilde \mathcal O n + n^ five/seven ε^ -two/seven $.

Sources in this cluster