A Probabilistic Approach to Neural Network Pruning
Authors: Xin Qian, Diego Klabjan
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In Appendix D we show some numerical results that support our theorems and assumptions. |
| Researcher Affiliation | Academia | Department of Industrial Engineering and Management Science, Northwestern University. |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any explicit statements or links about releasing their own source code. |
| Open Datasets | Yes | We train a 5-hidden-layer FCN with 1024 neurons in each hidden layer on the Covertype dataset (Blackard & Dean, 1998) by randomly selecting initial weights. |
| Dataset Splits | No | The paper mentions using the Covertype dataset but does not specify the train/validation/test splits. |
| Hardware Specification | No | The paper does not specify the hardware used to run the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies used in the experiments. |
| Experiment Setup | No | The paper mentions training a 5-hidden-layer FCN with 1024 neurons in each hidden layer and randomly selecting initial weights, but it does not provide specific hyperparameters (e.g., learning rate, batch size, optimizer) or detailed training configurations. |