ROI Maximization in Stochastic Online Decision-Making

Authors: Nicolò Cesa-Bianchi, Tom Cesari, Yishay Mansour, Vianney Perchet

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We introduce a novel theoretical framework for Return On Investment (ROI) maximization in repeated decision-making. Our algorithm provably converges to an optimal policy in class Π at a rate of order min{1/(N^2), N^1/3}, where N is the number of innovations and is the suboptimality gap in Π.
Researcher Affiliation Collaboration Nicolò Cesa-Bianchi Università degli Studi di Milano & DSRC nicolo.cesa-bianchi@unimi.it Tommaso Cesari Toulouse School of Economics tommaso.cesari@tse-fr.eu Yishay Mansour Tel Aviv University & Google research mansour@tau.ac.il Vianney Perchet CREST, ENSAE & Criteo AI Lab vianney.perchet@normalesup.org
Pseudocode Yes Algorithm 1: Capped Policy Elimination (CAPE) and Algorithm 2: Extension to Countable (ESC) are clearly presented as pseudocode blocks.
Open Source Code No The paper does not provide open-source code. The checklist states: 'Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]'
Open Datasets No The paper is theoretical and does not involve training on a dataset. The checklist states: 'Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]'
Dataset Splits No The paper is theoretical and does not involve dataset splits for validation. The checklist states: 'Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]'
Hardware Specification No The paper is theoretical and does not involve experiments requiring hardware specifications. The checklist states: 'Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A]'
Software Dependencies No The paper is theoretical and does not mention specific software dependencies with version numbers for experimental reproducibility. The checklist states: 'Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]'
Experiment Setup No The paper is theoretical and does not detail an experimental setup with hyperparameters or training settings. The checklist states: 'Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]'