4 papers
Riemannian AmbientFlow: Towards Simultaneous Manifold Learning and Generative Modeling from Corrupted Data
Willem Diepeveen, Oscar Leong
Modern generative modeling methods have demonstrated strong performance in learning complex data distributions from clean samples. In many scientific and imaging applications, howe…
Optimal Regularization Under Uncertainty: Distributional Robustness and Convexity Constraints
Oscar Leong, Eliza O'Reilly, Yong Sheng Soh
Regularization is a central tool for addressing ill-posedness in inverse problems and statistical estimation, with the choice of a suitable penalty often determining the reliabilit…
A Recovery Theory for Diffusion Priors: Deterministic Analysis of the Implicit Prior Algorithm
Oscar Leong, Yann Traonmilin
Recovering high-dimensional signals from corrupted measurements is a central challenge in inverse problems. Recent advances in generative diffusion models have shown remarkable emp…
The Star Geometry of Critic-Based Regularizer Learning
Oscar Leong, Eliza O'Reilly, Yong Sheng Soh
Variational regularization is a classical technique to solve statistical inference tasks and inverse problems, with modern data-driven approaches parameterizing regularizers via de…