Chris Cannella — accepted AI-conference papers

2021

Projected Latent Markov Chain Monte Carlo: Conditional Sampling of Normalizing Flows

Chris Cannella, Mohammadreza Soltani, Vahid Tarokh

ICLR 2021poster

We introduce Projected Latent Markov Chain Monte Carlo (PL-MCMC), a technique for sampling from the exact conditional distributions learned by normalizing flows. As a conditional sampling method, PL-MCMC enables Monte Carlo Expectation Maximization (MC-EM) training of normalizing flows from incomple…

Cited by 5 Source ↗PDF ↗Scholar ↗

2020

Perception-Distortion Trade-Off with Restricted Boltzmann Machines

Chris Cannella, Jie Ding, Mohammadreza Soltani, Yi Zhou, Vahid Tarokh

ICASSP 2020accepted

In this work, we introduce a new procedure for applying Restricted Boltzmann Machines (RBMs) to missing data inference tasks, based on linearization of the effective energy function governing the distribution of observations. We compare the performance of our proposed procedure with those obtained u…

Cited by 0 Source ↗Scholar ↗