4 papers
Learning Graph Energies for Finite-Time Generation
Amartya Banerjee, Xingyu Xu, Caroline Moosmüller +1
Energy-based models can represent distributions over discrete structures such as molecular graphs, but an energy that is accurate at equilibrium need not yield accurate samples whe…
Adaptive Multimodal Protein Plug-and-Play with Diffusion-Based Priors
Amartya Banerjee, Xingyu Xu, Caroline Moosmüller +1
In an inverse problem, the goal is to recover an unknown parameter (e.g., an image) that has typically undergone some lossy or noisy transformation during measurement. Recently, de…
Sparsity of Quadratically Regularized Optimal Transport: Bounds on concentration and bias
Johannes Wiesel, Xingyu Xu
We study the quadratically regularized optimal transport (QOT) problem for quadratic cost and compactly supported marginals and . It has been empirically observed that the o…
Agnostic Active Learning of Single Index Models with Linear Sample Complexity
Aarshvi Gajjar, Wai Ming Tai, Xingyu Xu +3
We study active learning methods for single index models of the form , where and ${\mathb…