collaborators

5 papers

math.OC2026

Projected gradient methods for nonconvex and stochastic smooth optimization: new complexities and auto-conditioned stepsizes

Guanghui Lan, Tianjiao Li, Yangyang Xu

We present a novel class of projected gradient (PG) methods for minimizing a smooth but not necessarily convex function over a convex compact set. We first provide a novel analysis…

math.OC2024

Auto-conditioned primal-dual hybrid gradient method and alternating direction method of multipliers

Guanghui Lan, Tianjiao Li

Line search procedures are often employed in primal-dual methods for bilinear saddle point problems, especially when the norm of the linear operator is large or difficult to comput…

cs.LG2024

Stochastic first-order methods for average-reward Markov decision processes

Tianjiao Li, Feiyang Wu, Guanghui Lan

We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluatio…

math.OC2024

Accelerated stochastic approximation with state-dependent noise

Sasila Ilandarideva, Anatoli Juditsky, Guanghui Lan +1

We consider a class of stochastic smooth convex optimization problems under rather general assumptions on the noise in the stochastic gradient observation. As opposed to the classi…

math.OC2024

A simple uniformly optimal method without line search for convex optimization

Tianjiao Li, Guanghui Lan

Line search (or backtracking) procedures have been widely employed into first-order methods for solving convex optimization problems, especially those with unknown problem paramete…