activity
20242026
collaborators

7 papers

cs.LG2026

Rollback-Free Stable Brick Structures Generation

Chenhui Xu, Ziyue Bai, Fuxun Yu +2

While autoregressive models have advanced 3D generation, creating physically stable brick structures remains a challenge due to the strict requirements of gravity and interconnecti…

cs.LG2026

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…

cs.LG2026

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…

cs.LG2025

Revisiting Zeroth-Order Optimization: Minimum-Variance Two-Point Estimators and Directionally Aligned Perturbations

Shaocong Ma, Heng Huang

In this paper, we explore the two-point zeroth-order gradient estimator and identify the distribution of random perturbations that minimizes the estimator's asymptotic variance as…

cs.LG2025

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…

cs.LG2025

Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality

Shaocong Ma, Ziyi Chen, Yi Zhou +1

The goal of robust constrained reinforcement learning (RL) is to optimize an agent's performance under the worst-case model uncertainty while satisfying safety or resource constrai…