4 papers
New Hybrid Fine-Tuning Paradigm for LLMs: Algorithm Design and Convergence Analysis Framework
Shaocong Ma, Peiran Yu, Heng Huang
Fine-tuning Large Language Models (LLMs) typically involves either full fine-tuning, which updates all model parameters, or Parameter-Efficient Fine-Tuning (PEFT), which adjusts a…
Riemannian Zeroth-Order Gradient Estimation with Structure-Preserving Metrics for Geodesically Incomplete Manifolds
Shaocong Ma, Heng Huang
In this paper, we study Riemannian zeroth-order optimization in settings where the underlying Riemannian metric is geodesically incomplete, and the goal is to approximate stati…
Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets
Shaocong Ma, Heng Huang
In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices. However, during deployment, thes…
On the Optimal Construction of Unbiased Gradient Estimators for Zeroth-Order Optimization
Shaocong Ma, Heng Huang
Zeroth-order optimization (ZOO) is an important framework for stochastic optimization when gradients are unavailable or expensive to compute. A potential limitation of existing ZOO…