4 papers
Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shift
Chengtao Jian, Kai Yang, Tianhao Gao +5
Direct Preference Learning has emerged as a dominant offline paradigm for preference optimization. Most of these methods are based on the Bradley-Terry (BT) model for pairwise pref…
UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimization
Kai Yang, Zelin Zhu, Chengtao Jian +4
Urban general intelligence (UGI) refers to the capacity of AI systems to autonomously perceive, reason, and act within dynamic and complex urban environments. In this paper, we int…
Unlocking TriLevel Learning with Level-Wise Zeroth Order Constraints: Distributed Algorithms and Provable Non-Asymptotic Convergence
Yang Jiao, Kai Yang, Chengtao Jian
Trilevel learning (TLL) found diverse applications in numerous machine learning applications, ranging from robust hyperparameter optimization to domain adaptation. However, existin…
Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
Chengtao Jian, Kai Yang, Yang Jiao
Out-of-Distribution (OOD) generalization in machine learning is a burgeoning area of study. Its primary goal is to enhance the adaptability and resilience of machine learning model…