Jan-Willem Meent — accepted AI-conference papers

2019

Structured Disentangled Representations

Babak Esmaeili, Hao Wu, Sarthak Jain, Alican Bozkurt, N Siddharth, Brooks Paige +3

AISTATS 2019poster

Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. Thes…

Cited by 169 Source ↗PDF ↗code ↗Scholar ↗

2015

Particle Gibbs with Ancestor Sampling for Probabilistic Programs

Jan-Willem Meent, Hongseok Yang, Vikash Mansinghka, Frank Wood

AISTATS 2015poster

Particle Markov chain Monte Carlo techniques rank among current state-of-the-art methods for probabilistic program inference. A drawback of these techniques is that they rely on importance resampling, which results in degenerate particle trajectories and a low effective sample size for variables sam…

Cited by 30 Source ↗PDF ↗Scholar ↗