6 papers
Extreme-Case Distorted Utility under Moment Ambiguity
Zehao Li, Yijie Peng, Hui Shao +1
Many operations decisions under distributional ambiguity, from pricing and inventory to capacity and contracting, evaluate an action through a tail-sensitive distorted utility of a…
Optimal low-rank stochastic gradient estimation for LLM training
Zehao Li, Tao Ren, Zishi Zhang +2
Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical…
Beyond likelihood ratio bias: Nested multi-time-scale stochastic approximation for likelihood-free parameter estimation
Zehao Li, Zhouchen Lin, Yijie Peng
We study parameter inference in simulation-based stochastic models where the analytical form of the likelihood is unknown. The main difficulty is that score evaluation as a ratio o…
Half-order Fine-Tuning for Diffusion Model: A Recursive Likelihood Ratio Optimizer
Tao Ren, Zishi Zhang, Jingyang Jiang +9
The probabilistic diffusion model (DM), generating content by inferencing through a recursive chain structure, has emerged as a powerful framework for visual generation. After pre-…
A New Stochastic Approximation Method for Gradient-based Simulated Parameter Estimation
Zehao Li, Yijie Peng
This paper tackles the challenge of parameter calibration in stochastic models, particularly in scenarios where the likelihood function is unavailable in an analytical form. We int…
Dual-Agent Deep Reinforcement Learning for Dynamic Pricing and Replenishment
Yi Zheng, Zehao Li, Peng Jiang +1
We study the dynamic pricing and replenishment problems under inconsistent decision frequencies. Different from the traditional demand assumption, the discreteness of demand and th…