Statistical Inference and A/B Testing for First-Price Pacing Equilibria

Authors: Luofeng Liao, Christian Kroer

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

Reproducibility Variable Result LLM Response
Research Type Experimental Numerical simulations verify our central limit theorems, and empirical coverage rates for our confidence intervals agree with our theory.
Researcher Affiliation Academia 1IEOR, Columbia University. Correspondence to: Luofeng Liao <ll3530@columbia.edu>.
Pseudocode Yes Algorithm 1 A/B test effect of a new feature on revenue
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper describes generating synthetic data for simulations (
Dataset Splits No The paper describes statistical simulations to verify theorems, not traditional machine learning training/validation/test splits of a pre-existing dataset. No specific dataset splits are mentioned for validation purposes.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments.
Software Dependencies No The paper does not list any specific software dependencies with version numbers.
Experiment Setup Yes We clearly see that (i) if β i < 1 then the finite sample distribution is close to a normal distribution, and (ii) if β i = 1 (or very close to 1, such as β14,21 in the uniform value plots, β20,23 in exponential), the finite sample distribution puts most of the probability mass at 1. For cases where β i is close to 1, we need to futher increase number of items to observe normality.