6 papers
DARE: Aligning LLM Agents with the R Statistical Ecosystem via Distribution-Aware Retrieval
Maojun Sun, Yue Wu, Yifei Xie +5
Large Language Model (LLM) agents can automate data-science workflows, but many rigorous statistical methods implemented in R remain underused because LLMs struggle with statistica…
dHPR: A Distributed Halpern Peaceman--Rachford Method for Non-smooth Distributed Optimization Problems
Zhangcheng Feng, Defeng Sun, Yancheng Yuan +1
This paper introduces the distributed Halpern Peaceman--Rachford (dHPR) method, an efficient algorithm for solving distributed convex composite optimization problems with non-smoot…
On the Relationships among GPU-Accelerated First-Order Methods for Solving Linear Programming
Kaihuang Chen, Defeng Sun, Yancheng Yuan +2
This paper aims to understand the relationships among recently developed GPU-accelerated first-order methods (FOMs) for linear programming (LP), with particular emphasis on HPR-LP…
HPR-QP: A dual Halpern Peaceman-Rachford method for solving large-scale convex composite quadratic programming
Kaihuang Chen, Defeng Sun, Yancheng Yuan +2
In this paper, we introduce HPR-QP, a dual Halpern Peaceman-Rachford (HPR) method designed for solving large-scale convex composite quadratic programming. One distinctive feature o…
HPR-LP: An implementation of an HPR method for solving linear programming
Kaihuang Chen, Defeng Sun, Yancheng Yuan +2
In this paper, we introduce an HPR-LP solver, an implementation of a Halpern Peaceman-Rachford (HPR) method with semi-proximal terms for solving linear programming (LP). The HPR me…
Peaceman-Rachford Splitting Method Converges Ergodically for Solving Convex Optimization Problems
Kaihuang Chen, Defeng Sun, Yancheng Yuan +2
In this paper, we prove that the ergodic sequence generated by the Peaceman-Rachford (PR) splitting method with semi-proximal terms converges for convex optimization problems (COPs…