5 papers
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…
Sharp Stability Threshold and Certification for Designing Stable Residual Architectures
Hyemin Gu, Michael Tyrrell, Tuhin Sahai +1
We propose \emph{the sublinear-growth principle} for deep residual architectures -- a sharp stability threshold on the input-magnitude exponent of every residual block's velocity f…
ISOMORPH: A Supply Chain Digital Twin for Simulation, Dataset Generation, and Forecasting Benchmarks
Zhizhen Zhang, Hyemin Gu, Benjamin J. Zhang +6
Open time-series forecasting (TSF) benchmarks cover retail, energy, weather, and traffic, but supply-chain logistics remains underserved. We introduce ISOMORPH, the first public di…
Combining Wasserstein-1 and Wasserstein-2 proximals: robust manifold learning via well-posed generative flows
Hyemin Gu, Markos A. Katsoulakis, Luc Rey-Bellet +1
We formulate well-posed continuous-time generative flows for learning distributions that are supported on low-dimensional manifolds through Wasserstein proximal regularizations of…
Robust Generative Learning with Lipschitz-Regularized -Divergences Allows Minimal Assumptions on Target Distributions
Ziyu Chen, Hyemin Gu, Markos A. Katsoulakis +2
This paper demonstrates the robustness of Lipschitz-regularized -divergences as objective functionals in generative modeling, showing they enable stable learning across a wide r…