3 papers
math.OC2026
Dimension-Free Complexity Guarantees for Dual Dynamic Programming
Pablo Barros, Vincent Guigues, Jiaming Liang +1
This paper studies the complexity of a dual dynamic programming (DDP) method for solving a class of convex optimization problems with linear coupling constraints. Existing complexi…
math.OC2025
Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method
Jiaming Liang
High-probability guarantees in stochastic optimization are often obtained only under strong noise assumptions such as sub-Gaussian tails. We show that such guarantees can also be a…
math.OC2025
Proximal Oracles for Optimization and Sampling
Jiaming Liang, Yongxin Chen
We consider convex optimization with non-smooth objective function and log-concave sampling with non-smooth potential (negative log density). In particular, we study two specific s…