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].
Functional vs. parametric equivalence of ReLU networks
Authors: Mary Phuong, Christoph H. Lampert
ICLR 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | The proof relies on a geometric understanding of boundaries between linear regions of Re LU networks, and we hope the developed mathematical tools are of independent interest. The full proof, including proofs of intermediate results, is included in the Appendix. |
| Researcher Affiliation | Academia | Mary Phuong & Christoph H. Lampert IST Austria Am Campus 1, Klosterneuburg, Austria EMAIL |
| Pseudocode | No | No pseudocode or algorithm blocks were found. |
| Open Source Code | No | No statement about open-source code release or repository links was found. |
| Open Datasets | No | This is a theoretical paper and does not use datasets for training or evaluation. |
| Dataset Splits | No | This is a theoretical paper and does not use dataset splits for validation. |
| Hardware Specification | No | This is a theoretical paper and does not describe computational experiments or specific hardware. |
| Software Dependencies | No | This is a theoretical paper and does not describe computational experiments or specific software dependencies. |
| Experiment Setup | No | This is a theoretical paper and does not describe experimental setups or hyperparameters. |