Beyond IID: data-driven decision-making in heterogeneous environments

Authors: Omar Besbes, Will Ma, Omar Mouchtaki

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we study data-driven decision-making and depart from the classical identically and independently distributed (i.i.d.) assumption. We present a new framework in which historical samples are generated from unknown and different distributions... We quantify the asymptotic worst-case regret... Our work shows that the type of achievable performance varies considerably... We demonstrate the versatility of our framework by comparing achievable guarantees... En route, we establish a new connection between data-driven decision-making and distributionally robust optimization.
Researcher Affiliation Academia Omar Besbes Will Ma Omar Mouchtaki Decision, Risk, and Operations Division Columbia University {ob2105,wm2428,om2316}@gsb.columbia.edu
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks. Policies like SAA are described in textual form.
Open Source Code No The paper does not provide any specific links or statements about the availability of open-source code for the described methodology.
Open Datasets No The paper does not mention using any specific public datasets for training, as it focuses on theoretical analysis and deriving performance bounds.
Dataset Splits No The paper does not provide details on dataset splits (train/validation/test), as it is a theoretical paper focusing on asymptotic analysis.
Hardware Specification No The paper does not provide any specific hardware details used for running experiments, as the research is theoretical and does not involve computational experiments that require such specifications.
Software Dependencies No The paper does not list specific software components with version numbers. This is consistent with its theoretical nature, which does not involve empirical implementation details.
Experiment Setup No The paper does not contain specific experimental setup details such as hyperparameters or training configurations, as it is a theoretical work and does not describe empirical experiments.