Longlin Yu
YOU?
Author Swipe
View article: Functional Gradient Flows for Constrained Sampling
Functional Gradient Flows for Constrained Sampling Open
Recently, through a unified gradient flow perspective of Markov chain Monte Carlo (MCMC) and variational inference (VI), particle-based variational inference methods (ParVIs) have been proposed that tend to combine the best of both worlds.…
View article: Diffusion-PINN Sampler
Diffusion-PINN Sampler Open
Recent success of diffusion models has inspired a surge of interest in developing sampling techniques using reverse diffusion processes. However, accurately estimating the drift term in the reverse stochastic differential equation (SDE) so…
View article: Kernel Semi-Implicit Variational Inference
Kernel Semi-Implicit Variational Inference Open
Semi-implicit variational inference (SIVI) extends traditional variational families with semi-implicit distributions defined in a hierarchical manner. Due to the intractable densities of semi-implicit distributions, classical SIVI often re…
View article: Reflected Flow Matching
Reflected Flow Matching Open
Continuous normalizing flows (CNFs) learn an ordinary differential equation to transform prior samples into data. Flow matching (FM) has recently emerged as a simulation-free approach for training CNFs by regressing a velocity model toward…
View article: Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration Open
Semi-implicit variational inference (SIVI) has been introduced to expand the analytical variational families by defining expressive semi-implicit distributions in a hierarchical manner. However, the single-layer architecture commonly used …
View article: Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
Particle-based Variational Inference with Generalized Wasserstein Gradient Flow Open
Particle-based variational inference methods (ParVIs) such as Stein variational gradient descent (SVGD) update the particles based on the kernelized Wasserstein gradient flow for the Kullback-Leibler (KL) divergence. However, the design of…
View article: Semi-Implicit Variational Inference via Score Matching
Semi-Implicit Variational Inference via Score Matching Open
Semi-implicit variational inference (SIVI) greatly enriches the expressiveness of variational families by considering implicit variational distributions defined in a hierarchical manner. However, due to the intractable densities of variati…