4 papers
Optimal Recursive Composition and Dyadic Phase Laws for Gradient Descent with Predetermined Stepsizes
Yu Liu, Kang Chen, Rujun Jiang +1
Predetermined stepsize schedules featuring carefully chosen long steps have recently been shown to accelerate gradient descent (GD) on smooth convex functions. A prominent class of…
Zeroth-order Stochastic Cubic Newton Method Revisited
Yu Liu, Weibin Peng, Tianyu Wang +1
This paper studies stochastic minimization of a finite-sum loss . In many real-world scenarios, the Hessian matrix of s…
Batched Stochastic Bandit for Nondegenerate Functions
Yu Liu, Yunlu Shu, Tianyu Wang
This paper studies batched bandit learning problems for nondegenerate functions. We introduce an algorithm that solves the batched bandit problem for nondegenerate functions near-o…
The Nesterov-Spokoiny Acceleration Achieves Strict 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…