11 papers
DSAEval: Evaluating Data Science Agents on a Wide Range of Real-World Data Science Problems
Maojun Sun, Yifei Xie, Yue Wu +5
Recent LLM-based data agents aim to automate data science tasks ranging from data analysis to deep learning. However, the open-ended nature of real-world data science problems, whi…
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…
A Survey on Large Language Model-based Agents for Statistics and Data Science
Maojun Sun, Ruijian Han, Binyan Jiang +4
In recent years, data science agents powered by Large Language Models (LLMs), known as "data agents," have shown significant potential to transform the traditional data analysis pa…
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…