Preprint

Simulation-based Inference via Langevin Dynamics with Score Matching
Simulation-based inference (SBI) enables Bayesian analysis when the likelihood is intractable but model simulations are available. …
Haoyu Jiang, Yuexi Wang, Yun Yang
PDF
Optimal Transport-Based Generative Models for Bayesian Posterior Sampling
We investigate the problem of sampling from posterior distributions with intractable normalizing constants in Bayesian inference. Our …
Ke Li, Wei Han, Yuexi Wang, Yun Yang
PDF
Pochhammer Priors for Sparse Count Models
Bayesian inference for Dirichlet-Multinomial (DM) models has a long and important history. The concentration parameter $\alpha$ is …
Yuexi Wang, Nicholas G. Polson
PDF
Adversarial Bayesian Simulation
In the absence of explicit or tractable likelihoods, Bayesians often resort to approximate Bayesian computation (ABC) for inference. …
Yuexi Wang, Veronika Rockova
PDF