Optimal Classification under Performative Distribution Shift

Authors: Edwige Cyffers, Muni Sreenivas Pydi, Jamal Atif, Olivier Cappé

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we test the performance of our algorithm Reparametrization-based Performative Gradient (RPPerf GD) with respect to existing algorithms. Three baselines were introduced in Perdomo et al. [2020]. First, Repeated Risk Minimization (RRM) computes at each step the next θ to minimize the non-performative risk, leading to the update rule θt+1 = arg minθ DPR(θt, θ ).
Researcher Affiliation Academia Edwige Cyffers Univ. Lille, Inria, CNRS, Centrale Lille, UMR 9189 CRISt AL, F-59000 Lille edwige.cyffers@inria.fr Muni Sreenivas Pydi Université Paris Dauphine, Université PSL, CNRS, LAMSADE, 75016 Paris Jamal Atif Université Paris Dauphine, Université PSL, CNRS, LAMSADE, 75016 Paris Oliver Cappé École Normale Supérieure, Université PSL, CNRS, Inria, DI ENS, 75005 Paris
Pseudocode Yes Algorithm 1: RPPerf GD with Π learning
Open Source Code No Justification: the code will be publicly released after publication
Open Datasets Yes We use the binarized version of the Housing dataset2, where the outcome is whether the price is high or not. ... 2https://www.openml.org/d/823
Dataset Splits No The paper mentions 'Sample size (n)' for datasets, but does not explicitly state specific training, validation, or test split percentages or sample counts in the main text or appendices for its experiments. While the NeurIPS checklist states 'Yes' for 'training and test details', the paper's content does not provide the explicit split information required by this question.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper does not provide specific version numbers for software dependencies or libraries used in the experiments.
Experiment Setup Yes Table 1: Parameters used for figure fig. 2b Parameter Value Number of iterations (num_iter) 100 Sample size (n) 1000 Scale (σ) 0.5 Average number of iterations (num_iter_average) 100 Step size (step_size) 0.1 Regularization parameter (λ) 3 10 2 ... Table 3: Parameters used for fig. 2f Parameter Value Number of iterations (num_iter) 15 Sample size (n) 18000 Number of runs (n_runs) 20 Step size (step_size) 0.2 Regularization parameter (λ) 5 10 3