Weibin Peng

collaborators

2 papers

math.OC2025

The Nesterov-Spokoiny Acceleration Achieves Strict $o (1/ k^{2})$ Convergence

Weibin Peng, Yu Liu, Tianyu Wang

This paper studies the Nesterov-Spokoiny Acceleration (NSA), a variant of the accelerated gradient method by Nesterov and Spokoiny. For smooth convex optimization, NSA achieves a s…

math.OC2025

Zeroth-order Stochastic Cubic Newton Method Revisited

Yu Liu, Weibin Peng, Tianyu Wang +1

This paper studies stochastic minimization of a finite-sum loss $F (x) = \frac{1}{N} \sum_{I^¾ = 1}^{N} f (x; I^¾)$ . In many real-world scenarios, the Hessian matrix of…

The Nesterov-Spokoiny Acceleration Achieves Strict o(1/k2) Convergence

Zeroth-order Stochastic Cubic Newton Method Revisited

The Nesterov-Spokoiny Acceleration Achieves Strict $o (1/ k^{2})$ Convergence