Causal Inference from Competing Treatments

Authors: Ana-Andreea Stoica, Vivian Yvonne Nastl, Moritz Hardt

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

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we build a game-theoretic model of agents who wish to estimate causal effects in the presence of competition, through a bidding system and a utility function that minimizes estimation error. Our main technical result establishes an approximation with a tractable objective that maximizes the sample value obtained through strategically allocating budget on subjects. This allows us to find an equilibrium in our model: we show that the tractable objective has a pure Nash equilibrium, and that any Nash equilibrium is an approximate equilibrium for our general objective that minimizes estimation error under broad conditions. The proofs for all results are detailed in the Appendix.
Researcher Affiliation Academia 1Social Foundations of Computation, Max Planck Institute for Intelligent Systems, Tübingen, Germany and Tübingen AI Center, Germany 2Department of Mathematics, ETH Zürich, Zürich, Switzerland. Correspondence to: Ana-Andreea Stoica <astoica@tuebingen.mpg.edu>, Vivian Yvonne Nastl <vivian.nastl@tuebingen.mpg.de>.
Pseudocode Yes Algorithm 1 Winning ranks for a subject slot t through the probabilistic allocation rule Aprob.
Open Source Code No The paper does not provide any statement about making its code open-source, nor does it include a link to a code repository.
Open Datasets No This paper is theoretical and does not conduct experiments on a public dataset. It defines a "data-generating process" as part of its theoretical model, but this is not an external, publicly available dataset.
Dataset Splits No The paper is theoretical and does not report on empirical experiments with dataset splits for training, validation, or testing.
Hardware Specification No The paper does not mention any specific hardware used for computations or experiments, as it is a theoretical work.
Software Dependencies No The paper does not specify any software dependencies with version numbers used for its theoretical derivations or model analysis.
Experiment Setup No The paper describes a theoretical model and game setup, including components like 'bidding system' and 'utility function', but it does not detail an 'experiment setup' in terms of hyperparameters or system-level training settings, as it does not report on empirical experiments.