Backpropagation of Unrolled Solvers with Folded Optimization
Authors: James Kotary, My H Dinh, Ferdinando Fioretto
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments over various model-based learning tasks demonstrate the advantages of the approach both computationally and in terms of enhanced expressiveness. This section evaluates folded optimization on four end-to-end optimization and learning tasks. |
| Researcher Affiliation | Academia | James Kotary1 , My H Dinh1 and Ferdinando Fioretto1 1 University of Virginia {jkotary, mydinh}@syr.edu, fioretto@virginia.edu |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions an 'accompanying Python library fold-opt' and states that 'Implementation details of fold-opt can be found in Appendix B.' of the extended version [Kotary et al., 2023b], but this paper does not provide a direct link to the code or explicitly state its public availability from this document. |
| Open Datasets | Yes | Mutilabel classification on CIFAR100. ... image feature embeddings c from Dense Net 40-40 [Huang et al., 2017] |
| Dataset Splits | No | The paper mentions the use of 'test set' in its experiments but does not provide specific details on the dataset splits (e.g., percentages, sample counts, or methodology for creating training, validation, and test sets). |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running experiments. |
| Software Dependencies | No | The paper mentions software like 'Python library fold-opt', 'Py Torch', 'Gurobi', and 'cvxpy' but does not specify their version numbers, which are necessary for reproducibility. |
| Experiment Setup | No | The paper refers to 'Implementation details' in Section 6 and directs to appendices of an extended version for 'more complete specification' and 'implementation details', but the main paper itself does not provide specific experimental setup details such as hyperparameters or system-level training settings. |