Nonstationary Dual Averaging and Online Fair Allocation

Authors: Luofeng Liao, Yuan Gao, Christian Kroer

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, numerical experiments show strong empirical performance of PACE against nonstationary inputs. In Appendix F we provide numerical experiments which corroborate the above theory and demonstrate the practical efficiency of PACE under different data input models.
Researcher Affiliation Academia Luofeng Liao, Yuan Gao, Christian Kroer IEOR, Columbia University {ll3530,yg254,ck294}@columbia.edu
Pseudocode Yes Algorithmic details are displayed in Algorithm 1. ... The algorithmic details for DA are presented in Algorithm 2.
Open Source Code Yes Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [Yes] See Appendix F.
Open Datasets No If your work uses existing assets, did you cite the creators? [No] We use synthetic data.
Dataset Splits Yes Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Appendix F.
Hardware Specification Yes Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [Yes] See Appendix F.
Software Dependencies No The paper does not explicitly state specific software dependencies with version numbers in the main text, nor is this information guaranteed by the checklist items without access to Appendix F.
Experiment Setup Yes Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [Yes] See Appendix F.