6 papers
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Yuyao Ge, Shenghua Liu, Peizhong Gao +8
Agents driven by large language models are increasingly deployed on long-horizon tasks, where they use tools and modify real workspaces. How well they perform depends as much on th…
Optimal Convex Optimization with Inexact Second-Order Oracles
Lesi Chen, Chengchang Liu, Luo Luo +2
In this paper, we present a novel second-order method called Accelerated Inexact Newton Extragradient (AINE) for convex optimization using -inexact Hessians. We show that AINE c…
Solving Convex-Concave Problems with Second-Order Oracle Complexity
Lesi Chen, Chengchang Liu, Luo Luo +1
Previous algorithms can solve convex-concave minimax problems with second-order oracle calls usin…
Faster Newton Methods for Convex and Nonconvex Optimization in Gradient Complexity
Lesi Chen, Chengchang Liu, Luo Luo +1
Second-order optimization methods are computationally expensive for large-scale problems. Recently, Doikov, Chayti, and Jaggi (ICML 2023) proposed the LazyCRN method that reduces c…
An Enhanced Levenberg--Marquardt Method via Gram Reduction
Chengchang Liu, Luo Luo, John C. S. Lui
This paper studied the problem of solving the system of nonlinear equations , where . We propose Gram-Reduced Lev…
On the Complexity of Finite-Sum Smooth Optimization under the Polyak-Łojasiewicz Condition
Yunyan Bai, Yuxing Liu, Luo Luo
This paper considers the optimization problem of the form , where satisfies the…