Ariel Boyarsky
Research Subjects
Ariel Boyarsky has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Hongseok Namkoong
Decision, Risk, and Operations Division, Columbia University, New York, New York 10027
2 shared publications - Jean Pouget-Abadie
Google Research, New York, NY, USA
2 shared publications P. Go´ra
Department of Mathematics, Loyola Campus, Concordia University, 7141 Sherbrooke St West, Montreal, CanadaH4B 1R6
1 shared publication
Latest Publications
- Open Access
Modeling Interference Using Experiment Roll-out
Experiments on online marketplaces and social networks suffer from interference, where the outcome of a unit is impacted by the treatment status of other units. We propose a framework for modeling interference using a ubiquitous deployment mechanism for experiments, staggered roll-out designs, which slowly increase the fraction of units exposed to the treatment to mitigate any unanticipated adverse side effects. Our main idea is to leverage the temporal variations in treatment assignments introduced by roll-outs to model the interference structure. Since there are often multiple competing models of interference in practice we first develop a model selection method that evaluates models based on their ability to explain outcome variation observed along the roll-out. Through simulations, we show that our heuristic model selection method, Leave-One-Period-Out, outperforms other baselines. Next, we present a set of model identification conditions under which the estimation of common estimands is possible and show how these conditions are aided by roll-out designs. We conclude with a set of considerations, robustness checks, and potential limitations for practitioners wishing to use our framework.
Open AccessModeling Interference Using Experiment Roll-out
Experiments on online marketplaces and social networks suffer from interference, where the outcome of a unit is impacted by the treatment status of other units. We propose a framework for modeling interference using a ubiquitous deployment mechanism for experiments, staggered roll-out designs, which slowly increase the fraction of units exposed to the treatment to mitigate any unanticipated adverse side effects. Our main idea is to leverage the temporal variations in treatment assignments introduced by roll-outs to model the interference structure. Since there are often multiple competing models of interference in practice we first develop a model selection method that evaluates models based on their ability to explain outcome variation observed along the roll-out. Through simulations, we show that our heuristic model selection method, Leave-One-Period-Out, outperforms other baselines. Next, we present a set of model identification conditions under which the estimation of common estimands is possible and show how these conditions are aided by roll-out designs. We conclude with a set of considerations, robustness checks, and potential limitations for practitioners wishing to use our framework.
- Open Access
- 7 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 298
Modeling Interference Using Experiment Roll-out
Experimentation is the foundation of scientific decision-making on online marketplaces and social networks. However, experiments often suffer from interference where intervening on a participant impacts the outcome of other participants. Under general interference, the causal effect cannot be identified even in a randomized experiment. Interference is especially problematic in marketplaces, where strategic agents compete for scarce resources. For example, consider an experiment comparing two different policies for selecting the reserve price in a second-price advertising auction. Changes in the reserve price ("treatment / intervention") for some advertisers (bidders) can affect other advertisers through market competition, impacting the outcomes of even untreated advertisers.
- 7 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 298
Open AccessModeling Interference Using Experiment Roll-out
Experimentation is the foundation of scientific decision-making on online marketplaces and social networks. However, experiments often suffer from interference where intervening on a participant impacts the outcome of other participants. Under general interference, the causal effect cannot be identified even in a randomized experiment. Interference is especially problematic in marketplaces, where strategic agents compete for scarce resources. For example, consider an experiment comparing two different policies for selecting the reserve price in a second-price advertising auction. Changes in the reserve price ("treatment / intervention") for some advertisers (bidders) can affect other advertisers through market competition, impacting the outcomes of even untreated advertisers.
- Open Access
- 1 January 2006
- Published by Wiley in Discrete Dynamics in Nature and Society
- Vol. 2006 (1) , 1-6
A discrete‐time interpretation of the Planck‐Einstein equation
An important conclusion of both string theory and loop quantum gravity theory is that space and time are ultimately discrete. A consequence of discrete space is that there is empty space between the basic elements of space. Analogously, there are empty times between the times where time exists. When time does not exist, it is meaningless to consider the existence of the universe. In this note we consider a discrete‐time interpretation of the Planck‐Einstein equation and draw a curious conclusion about the real age of the universe.
- 1 January 2006
- Published by Wiley in Discrete Dynamics in Nature and Society
- Vol. 2006 (1) , 1-6
Open AccessA discrete‐time interpretation of the Planck‐Einstein equation
An important conclusion of both string theory and loop quantum gravity theory is that space and time are ultimately discrete. A consequence of discrete space is that there is empty space between the basic elements of space. Analogously, there are empty times between the times where time exists. When time does not exist, it is meaningless to consider the existence of the universe. In this note we consider a discrete‐time interpretation of the Planck‐Einstein equation and draw a curious conclusion about the real age of the universe.
- 1 May 1996
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 7 (5) , 611-630
A model for the structure of spacetime
- 1 May 1996
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 7 (5) , 611-630
A model for the structure of spacetime