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].
Unsupervised Learning for Solving the Travelling Salesman Problem
Authors: Yimeng Min, Yiwei Bai, Carla P. Gomes
NeurIPS 2023 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that UTSP outperforms the existing data-driven TSP heuristics. |
| Researcher Affiliation | Academia | Yimeng Min Dept. of Computer Science Cornell University Ithaca, NY, USA EMAIL Yiwei Bai Dept. of Computer Science Cornell University Ithaca, NY, USA EMAIL Carla P. Gomes Dept. of Computer Science Cornell University Ithaca, NY, USA EMAIL |
| Pseudocode | No | The paper describes its methods through prose and mathematical equations but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating the availability of open-source code for the described methodology. |
| Open Datasets | Yes | Our dataset contains 2,000 samples for training and 1,000 samples for validation. We use the same test dataset in Fu et al. [2021]. |
| Dataset Splits | Yes | Our dataset contains 2,000 samples for training and 1,000 samples for validation. |
| Hardware Specification | Yes | All models are trained using Nvidia V100 GPU. |
| Software Dependencies | No | The paper mentions using Adam optimizer but does not specify any software names with version numbers for reproducibility (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | All the search-related parameters are listed in Table 4. M is the size of the candidate set of each city. K is the maximal number of edges we can remove in one action, and for each round of local search, we randomly select one number from the listed interval. T is the total number of actions we will try to expand one node. |