Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
The Thermodynamic Variational Objective
Authors: Vaden Masrani, Tuan Anh Le, Frank Wood
NeurIPS 2019 | Venue PDF | 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}. |