Last-iterate convergent policy gradient primal-dual methods for constrained mdps
We study the problem of computing an optimal policy of an infinite-horizon discounted
constrained Markov decision process (constrained MDP). Despite the popularity of …
constrained Markov decision process (constrained MDP). Despite the popularity of …
A primal-dual flow for affine constrained convex optimization
H Luo - ESAIM: Control, Optimisation and Calculus of …, 2022 - esaim-cocv.org
We introduce a novel primal-dual flow for affine constrained convex optimization problems.
As a modification of the standard saddle-point system, our flow model is proved to possess …
As a modification of the standard saddle-point system, our flow model is proved to possess …
A unified differential equation solver approach for separable convex optimization: splitting, acceleration and nonergodic rate
H Luo, Z Zhang - Mathematics of Computation, 2025 - ams.org
This paper provides a self-contained ordinary differential equation solver approach for
separable convex optimization problems. A novel primal-dual dynamical system with built-in …
separable convex optimization problems. A novel primal-dual dynamical system with built-in …
A universal accelerated primal–dual method for convex optimization problems
H Luo - Journal of Optimization Theory and Applications, 2024 - Springer
This work presents a universal accelerated primal–dual method for affinely constrained
convex optimization problems. It can handle both Lipschitz and Hölder gradients but does …
convex optimization problems. It can handle both Lipschitz and Hölder gradients but does …
Preprocessing and First-Order Primal-Dual Algorithms for Convex Optimization
Y Zhu - 2020 - search.proquest.com
PREPROCESSING AND FIRST-ORDER PRIMAL-DUAL ALGORITHMS FOR CONVEX
OPTIMIZATION Yuzixuan Zhu A dissertation submitted to the facult Page 1 PREPROCESSING …
OPTIMIZATION Yuzixuan Zhu A dissertation submitted to the facult Page 1 PREPROCESSING …