The Thermodynamic Variational Objective

Authors: Vaden Masrani, Tuan Anh Le, Frank Wood

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We use the TVO to learn both discrete and continuous deep generative models and empirically demonstrate state of the art model and inference network learning.
Researcher Affiliation Academia Vaden Masrani1, Tuan Anh Le2, Frank Wood1 1Department of Computer Science, University of British Columbia 2Department of Brain and Cognitive Sciences, MIT
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes Code to reproduce all experiments is available at: https://github.com/vmasrani/tvo.
Open Datasets Yes We use the binarized MNIST dataset with the standard train/validation/test split of 50k/10k/10k [35].
Dataset Splits Yes We use the binarized MNIST dataset with the standard train/validation/test split of 50k/10k/10k [35].
Hardware Specification No The paper acknowledges support from Compute Canada and Intel, but does not specify exact hardware models (e.g., GPU/CPU models, memory) used for the experiments.
Software Dependencies No The paper mentions using the Adam optimizer but does not specify version numbers for any software or libraries used in the implementation.
Experiment Setup Yes We train a sigmoid belief network, described in detail in Appendix I, using the TVO with the Adam optimizer. ... For each value of β1 we train the discrete generative model for K 2 {2, 5, 10, . . . , 50} and S 2 {2, 5, 10, 50}.