Coupled Gradient Estimators for Discrete Latent Variables

Authors: Zhe Dong, Andriy Mnih, George Tucker

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In systematic experiments, we show that our proposed categorical gradient estimators provide state-of-the-art performance, whereas even with additional Rao-Blackwellization, previous estimators (Yin et al., 2019) underperform a simpler REINFORCE with a leave-one-out-baseline estimator (Kool et al., 2019).
Researcher Affiliation Industry Zhe Dong Google Research, Brain Team zhedong@google.com Andriy Mnih Deep Mind andriy@deepmind.com George Tucker Google Research, Brain Team gjt@google.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code and additional information: https://sites.google.com/view/disarm-estimator.
Open Datasets Yes on three datasets: binarized MNIST (Le Cun et al., 2010), Fashion MNIST (Xiao et al., 2017), and Omniglot (Lake et al., 2015).
Dataset Splits Yes We use the standard split into train, validation, and test sets.
Hardware Specification No The paper does not explicitly describe the specific hardware (e.g., GPU/CPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions TensorFlow Probability without a version number and does not list other specific software dependencies with version numbers.
Experiment Setup Yes For most experiments, we used 32 latent variables with 64 categories unless specified otherwise. See Appendix A.2 for more details.