3 papers
cs.CV2026
DT-LoRA: Reaching Beyond the Tangent Space of Low-Rank Adaptation
Yangming Zhang, Ling Yi, Datong Li +4
Low-rank adaptation (LoRA) often underperforms full fine-tuning. We investigate this performance gap through a tangent-space lens: factorized updates are confined to the tangent sp…
eess.SY2024
Reduced Network Cumulative Constraint Violation for Distributed Bandit Convex Optimization under Slater Condition
Kunpeng Zhang, Xinlei Yi, Jinliang Ding +3
This paper studies the distributed bandit convex optimization problem with time-varying inequality constraints, where the goal is to minimize network regret and cumulative constrai…
cs.NE2023
Solving Expensive Optimization Problems in Dynamic Environments with Meta-learning
Huan Zhang, Jinliang Ding, Liang Feng +2
Dynamic environments pose great challenges for expensive optimization problems, as the objective functions of these problems change over time and thus require remarkable computatio…