Non-Convex Bilevel Games with Critical Point Selection Maps

Authors: Michael Arbel, Julien Mairal

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we show that algorithms for solving bilevel problems based on unrolled optimization solve these games up to approximation errors due to finite computational power. A simple correction to these algorithms is then proposed for removing these errors. and Numerical results illustrating the benefits of the correction are presented in Appendix E.
Researcher Affiliation Academia Michael Arbel and Julien Mairal Univ. Grenoble Alpes, Inria, CNRS, Grenoble INP, LJK, 38000 Grenoble, France
Pseudocode Yes Algorithm 1 BGS-Opt(x0, y0)
Open Source Code No The paper does not provide explicit statements or links to open-source code for the described methodology. The checklist indicates 'N/A' for inclusion of code.
Open Datasets No The paper mentions applications in machine learning but does not provide concrete access information (link, DOI, formal citation) for any specific dataset used in its numerical results.
Dataset Splits No The paper focuses on theoretical aspects and algorithm design; it does not specify training, validation, or test dataset splits for any experiments conducted by the authors.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers needed to replicate the experiment.
Experiment Setup No The paper does not provide specific experimental setup details such as hyperparameter values or training configurations.