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].
Exactly Computing the Local Lipschitz Constant of ReLU Networks
Authors: Matt Jordan, Alexandros G. Dimakis
NeurIPS 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate our algorithm on various applications. We evaluate a variety of Lipschitz estimation techniques to definitively evaluate their relative error compared to the true Lipschitz constant. We apply our algorithm to yield reliable empirical insights about how changes in architecture and various regularization schemes affect the Lipschitz constants of Re LU networks. |
| Researcher Affiliation | Academia | Matt Jordan UT Austin EMAIL Alexandros G. Dimakis UT Austin EMAIL |
| Pseudocode | No | The paper describes the algorithmic steps in narrative text, for example, 'To put all the above components together, we summarize our algorithm.' However, it does not include a formally structured pseudocode block or an algorithm figure. |
| Open Source Code | No | The paper does not include an unambiguous statement about releasing source code for the methodology or provide a link to a code repository. |
| Open Datasets | Yes | We evaluate each technique over the unit hypercube across random networks, networks trained on synthetic datasets, and networks trained to distinguish between MNIST 1 s and 7 s. |
| Dataset Splits | No | The paper mentions evaluating techniques on 'random networks, networks trained on synthetic datasets, and networks trained to distinguish between MNIST 1 s and 7 s.' However, it does not provide specific dataset split information (e.g., percentages, sample counts, or explicit splitting methodology) for training, validation, and testing. |
| Hardware Specification | No | The acknowledgments mention 'computing resources from TACC', but the paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running its experiments. |
| Software Dependencies | No | The paper mentions 'Pytorch s automatic differentiation package' and 'Tensorflow', and refers to 'Mixed-Integer Program (MIP) solvers', but it does not provide specific software names with version numbers (e.g., 'PyTorch 1.9') for its ancillary software dependencies. |
| Experiment Setup | No | The paper states, 'Full descriptions of the computing environment and experimental details are contained in the supplementary.' However, the main text does not provide specific experimental setup details, such as concrete hyperparameter values, model initialization, or training configurations. |