Demographic Parity Constrained Minimax Optimal Regression under Linear Model

Authors: Kazuto Fukuchi, Jun Sakuma

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our analysis reveals that the minimax optimal error for the demographic parity-constrained regression problem under our model is characterized by Θ(d M/n), where n denotes the sample size, d represents the dimensionality, and M signifies the number of demographic groups arising from sensitive attributes. Moreover, we demonstrate that the minimax error increases in conjunction with a larger bias present in the model.
Researcher Affiliation Academia Kazuto Fukuchi1,3 Jun Sakuma2,3 1 University of Tsukuba 2 Tokyo Institute of Technology 3 RIKEN
Pseudocode Yes Algorithm 1: Algorithm of the proposed optimal estimator.
Open Source Code No The paper does not include any statements about making its source code available or provide links to a code repository.
Open Datasets No The paper is theoretical and does not describe experiments using specific datasets, thus no information about public dataset availability for training is provided.
Dataset Splits No The paper is theoretical and does not describe empirical experiments with data, so no training/test/validation splits are mentioned.
Hardware Specification No The paper describes theoretical analysis and does not mention any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not mention any specific software dependencies with version numbers for implementation or experiments.
Experiment Setup No The paper is theoretical and focuses on mathematical derivations and proofs, thus it does not describe an experimental setup with hyperparameters or training configurations.