8 papers
Robust Wasserstein barycenter
Zixiong Cheng, Hang Liu
In this paper, we address a fundamental limitation of the classical Wasserstein barycenter -- its sensitivity to outliers. To overcome these issues, we propose the robust Wasserste…
MePoly: Max Entropy Polynomial Policy Optimization
Hang Liu, Sangli Teng, Maani Ghaffari
Stochastic Optimal Control provides a unified mathematical framework for solving complex decision-making problems, encompassing paradigms such as maximum entropy reinforcement lear…
Training-Free Adaptation of Diffusion Models via Doob's -Transform
Qijie Zhu, Zeqi Ye, Han Liu +2
Adaptation methods have been a workhorse for unlocking the transformative power of pre-trained diffusion models in diverse applications. Existing approaches often abstract adaptati…
Multidimensional Stochastic Dominance Test Based on Center-outward Quantiles
Yiming Ma, Hang Liu, Weiwei Zhuang
Stochastic dominance (SD) provides a quantile-based partial ordering of random variables and has broad applications. Its extension to multivariate settings, however, is challenging…
E-ROBOT: a dimension-free method for robust statistics and machine learning via Schrödinger bridge
Davide La Vecchia, Hang Liu
We propose the Entropic-regularized Robust Optimal Transport (E-ROBOT) framework, a novel method that combines the robustness of ROBOT with the computational and statistical benefi…
PolicyEvolve: Evolving Programmatic Policies by LLMs for multi-player games via Population-Based Training
Mingrui Lv, Hangzhi Liu, Zhi Luo +2
Multi-agent reinforcement learning (MARL) has achieved significant progress in solving complex multi-player games through self-play. However, training effective adversarial policie…