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 [1].
From Boltzmann Machines to Neural Networks and Back Again
Authors: Surbhi Goel, Adam Klivans, Frederic Koehler
NeurIPS 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Lastly, we present an experimental evaluation of our "supervised RBM" algorithm on MNIST and Fashion MNIST to highlight the applicability of our techniques in practice (Section 5). In this section we present some simple experiments on MNIST and Fashion MNIST to conο¬rm that our method performs reasonably well in practice. |
| Researcher Affiliation | Collaboration | Surbhi Goel Microsoft Research NYC EMAIL Adam Klivans University of Texas at Austin EMAIL Frederic Koehler MIT EMAIL |
| Pseudocode | Yes | Algorithm 1 LEARNSUPERVISEDRBMNBHD(u, Ο, S) (Adapted from [18, 19]) |
| Open Source Code | No | The paper does not contain an explicit statement or link providing access to open-source code for the described methodology. |
| Open Datasets | Yes | Lastly, we present an experimental evaluation of our "supervised RBM" algorithm on MNIST and Fashion MNIST to highlight the applicability of our techniques in practice (Section 5). For Fashion MNIST, we obtained a test accuracy of 88.84 0.31%; the training accuracy was 92.19% and we trained the logistic regression for 45 epochs with L-BFGS as before. Both datasets have 60,000 training points and 10,000 test; |
| Dataset Splits | No | The paper states: "Both datasets have 60,000 training points and 10,000 test;" but does not specify a validation set split. |
| Hardware Specification | Yes | Overall training took a bit less than an hour each on a Kaggle notebook with a P100 GPU. |
| Software Dependencies | No | The paper mentions "logistic regression", "L-BFGS", and "Gibbs sampling" but does not specify software names with version numbers (e.g., Python, PyTorch, TensorFlow, or scikit-learn versions). |
| Experiment Setup | Yes | we trained the logistic regression for 30 epochs (same as steps) of L-BFGS with line search enabled. For Fashion MNIST, we obtained a test accuracy of 88.84 0.31%; the training accuracy was 92.19% and we trained the logistic regression for 45 epochs with L-BFGS as before. Overall training took a bit less than an hour each on a Kaggle notebook with a P100 GPU. in both experiments we used a maximum neighborhood size of 12, and stopped adding neighbors if the conditional variance shrunk by less than 1%. |