5 papers
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…
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…
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…
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…
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…