6 papers
Nonmonotone Coderivative-Based Newton Methods for Nonsmooth Optimization with Machine Learning Applications
Sina Kazemdehbashi, Yanchao Liu, Boris S. Mordukhovich
Newton-type algorithms are among the most effective methods for solving optimization problems because of their rapid local convergence. However, extending these methods to nonsmoot…
AQuA: Recursively Self-Improving Quantitative Trading Research Agents
Jiacheng Guo, Suozhi Huang, Yunlong Gao +5
We study recursive self-improvement at the level of quantitative-investment research: whether an autonomous system can use evidence from earlier experiments to improve the hypothes…
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
Jiacheng Guo, Suozhi Huang, Zixin Yao +16
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in t…
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Zihao Li, Yuan Cao, Cheng Gao +5
Transformers have achieved great success in recent years. Interestingly, transformers have shown particularly strong in-context learning capability -- even without fine-tuning, the…
Global Convergence in Training Large-Scale Transformers
Cheng Gao, Yuan Cao, Zihao Li +5
Despite the widespread success of Transformers across various domains, their optimization guarantees in large-scale model settings are not well-understood. This paper rigorously an…
Regularized DeepIV with Model Selection
Zihao Li, Hui Lan, Vasilis Syrgkanis +2
In this paper, we study nonparametric estimation of instrumental variable (IV) regressions. While recent advancements in machine learning have introduced flexible methods for IV es…