Strategic Classification in the Dark

Authors: Ganesh Ghalme, Vineet Nair, Itay Eilat, Inbal Talgam-Cohen, Nir Rosenfeld

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We complement our theoretical results with experiments on synthetic data as well as on a large dataset of loan requests.
Researcher Affiliation Academia Ganesh Ghalme * 1 Vineet Nair * 1 Itay Eilat 1 Inbal Talgam-Cohen 1 Nir Rosenfeld 1 *Equal contribution 1Technion Israel Institute of Technology. Correspondence to: Ganesh Ghalme <ganeshg@campus.technion.ac.il>, Vineet Nair <vineet@cs.technion.ac.il>.
Pseudocode No The paper describes algorithms verbally and mathematically, but no structured pseudocode or algorithm blocks are provided.
Open Source Code Yes Code is publicly available at https://github.com/ staretgicclfdark/strategic_rep.
Open Datasets Yes We now turn to studying the Prosper loans dataset. ... The data includes n = 20, 222 examples, which we partition 70 15 15 into three sets: a training set T for Jury, a held-out test-set S, and a pool of samples from which we sample points for each TC(x), x S.
Dataset Splits Yes The data includes n = 20, 222 examples, which we partition 70 15 15 into three sets: a training set T for Jury, a held-out test-set S, and a pool of samples from which we sample points for each TC(x), x S.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments.
Software Dependencies No The paper mentions using 'SVM' and the 'algorithm of Hardt et al. (2016)' but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, scikit-learn versions).
Experiment Setup No The paper describes the general experimental setting and the models used, but it does not provide specific hyperparameters or system-level training settings like learning rates, batch sizes, or number of epochs.