Timezone: »

A Langevin-like Sampler for Discrete Distributions
Ruqi Zhang · Xingchao Liu · Qiang Liu

Tue Jul 19 03:30 PM -- 05:30 PM (PDT) @ Hall E #715

We propose discrete Langevin proposal (DLP), a simple and scalable gradient-basedproposal for sampling complex high-dimensional discrete distributions. In contrast to Gibbs sampling-based methods, DLP is able to update all coordinates in parallel in a single step and the magnitude of changes is controlled by a stepsize. This allows a cheap and efficient exploration in the space of high-dimensional and strongly correlated variables. We prove the efficiency of DLP by showing that the asymptotic bias of its stationary distribution is zero for log-quadratic distributions, and is small for distributions that are close to being log-quadratic. With DLP, we develop several variants of sampling algorithms, including unadjusted, Metropolis-adjusted, stochastic and preconditioned versions. DLP outperforms many popular alternatives on a wide variety of tasks, including Ising models, restricted Boltzmann machines, deep energy-based models, binary neural networks and language generation.

Author Information

Ruqi Zhang (UT Austin/Purdue)
Xingchao Liu (University of Texas at Austin)
Qiang Liu (UT Austin)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors