Maximizing the Success Probability of Policy Allocations in Online Systems

Authors: Artem Betlei, Mariia Vladimirova, Mehdi Sebbar, Nicolas Urien, Thibaud Rahier, Benjamin Heymann

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we conduct comprehensive experiments both on synthetic and real-world data to evaluate its performance. The results demonstrate that our proposed algorithm outperforms conventional expected-value maximization algorithms in terms of success rate.
Researcher Affiliation Industry 1 Criteo AI Lab, France 2 Criteo Ad Landscape, France {a.betlei, m.vladimirova, m.sebbar, n.urien, t.rahier, b.heymann}@criteo.com
Pseudocode Yes Algorithm 1: Success Proba Max
Open Source Code Yes source code3 is published to reproduce all the empirical results. 3https://github.com/criteo-research/success-proba-max
Open Datasets Yes CRITEO-UPLIFT v2 (Diemert et al. 2021) is provided by the Ad Tech company Criteo.
Dataset Splits No The paper states: 'Finally, we randomly partitioned dataset into two equal parts for train and test.' It does not explicitly mention a separate validation split.
Hardware Specification No The paper mentions using the JAX framework but does not specify any hardware details like GPU/CPU models or other computing infrastructure used for experiments.
Software Dependencies No The paper mentions using the 'JAX framework' but does not provide specific version numbers for JAX or any other software dependencies.
Experiment Setup Yes Hyperparameters used for the methods are provided in Supplementary material and source code3 is published to reproduce all the empirical results.