Description
Kernel density matrices provide a simpler yet effective mechanism for representing joint probability distributions of both continuous and discrete random variables. This abstraction allows the construction of differentiable models for density estimation, inference, and sampling, and enables their integration into end-to-end deep neural models.
Papers Using This Method
One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling2025-05-19Kernel Density Machines2025-04-30Key-point Guided Deformable Image Manipulation Using Diffusion Model2024-01-16DisCover: Disentangled Music Representation Learning for Cover Song Identification2023-07-19Kernel Density Matrices for Probabilistic Deep Learning2023-05-26