← Search

Srinivas Vasudevan

2 accepted papers

2022

MCMC Should Mix: Learning Energy-Based Model with Neural Transport Latent Space MCMC

ICLR 2022poster

Learning energy-based model (EBM) requires MCMC sampling of the learned model as an inner loop of the learning algorithm. However, MCMC sampling of EBMs in high-dimensional data space is generally not mixing, because the energy function, which is usually parametrized by deep network, is highly multi…

Cited by 31Source ↗PDF ↗Scholar ↗
2018

Simple, Distributed, and Accelerated Probabilistic Programming

NeurIPS 2018poster

We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single abstraction—the random variable. Our lightweight implementation in TensorFlow enables numerous applications: a model-par…