Ziyu Chen

collaborators

Showing stat.MLShow all

3 papers · 1 filter

stat.ML2026

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows

Thejani Gamage, Hyemin Gu, Zhizhen Zhang +3

We propose CVaR-penalized Generative Particle Algorithm (CVaR-GPA), a robust, tail-agnostic algorithm for fine-tuning generative models to learn heavy-tailed distributions and capt…

stat.ML2026

Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences

Ziyu Chen, Markos A. Katsoulakis, Benjamin J. Zhang

We introduce a novel Wasserstein-1 ( $W_{1}$ ) path-space divergence for stochastic and deterministic dynamics and establish a Wasserstein Uncertainty Propagation (WUP) theorem that bo…

stat.ML2025

Robust Generative Learning with Lipschitz-Regularized $I^\pm$ -Divergences Allows Minimal Assumptions on Target Distributions

Ziyu Chen, Hyemin Gu, Markos A. Katsoulakis +2

This paper demonstrates the robustness of Lipschitz-regularized $I^\pm$ -divergences as objective functionals in generative modeling, showing they enable stable learning across a wide…

Fine-Tuning Generative Models for Extreme Events via CVaR-Penalized Wasserstein Gradient Flows

Robustness and Structure Preservation in Flow-Based Generative Models via Wasserstein Path-Space Divergences

Robust Generative Learning with Lipschitz-Regularized I^±-Divergences Allows Minimal Assumptions on Target Distributions

Robust Generative Learning with Lipschitz-Regularized $I^\pm$ -Divergences Allows Minimal Assumptions on Target Distributions