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 …
outcome of a unit is impacted by the treatment status of other units. We propose a framework …
On online experimentation without device identifiers
Measuring human feedback via randomized experimentation is a cornerstone of data-driven
decision-making. The methodology used to estimate user preferences from their online …
decision-making. The methodology used to estimate user preferences from their online …
Experimental design for causal inference through an optimization lens
J Zhao - … in Operations Research: Smarter Decisions for a …, 2024 - pubsonline.informs.org
The study of experimental design offers tremendous benefits for answering causal questions
across a wide range of applications, including agricultural experiments, clinical trials …
across a wide range of applications, including agricultural experiments, clinical trials …
A/B testing under Interference with Partial Network Information
A/B tests are often required to be conducted on subjects that might have social connections.
For eg, experiments on social media, or medical and social interventions to control the …
For eg, experiments on social media, or medical and social interventions to control the …
Causal Inference in Social Platforms Under Approximate Interference Networks
Estimating the total treatment effect (TTE) of a new feature in social platforms is crucial for
understanding its impact on user behavior. However, the presence of network interference …
understanding its impact on user behavior. However, the presence of network interference …
Cascade-based Randomization for Inferring Causal Effects under Diffusion Interference
The presence of interference, where the outcome of an individual may depend on the
treatment assignment and behavior of neighboring nodes, can lead to biased causal effect …
treatment assignment and behavior of neighboring nodes, can lead to biased causal effect …
Causal Inference under Network Interference Using a Mixture of Randomized Experiments
Y Jiang, H Wang - arxiv preprint arxiv:2309.00141, 2023 - arxiv.org
In randomized experiments, the classic stable unit treatment value assumption (SUTVA)
states that the outcome for one experimental unit does not depend on the treatment …
states that the outcome for one experimental unit does not depend on the treatment …
Country-diverted experiments for mitigation of network effects
For large content platforms, user-diverted A/B experimentation has become the standard
way of evaluating impact of recommendation system changes on audience engagement and …
way of evaluating impact of recommendation system changes on audience engagement and …
The Conflict Graph Design: Estimating Causal Effects under Arbitrary Neighborhood Interference
A fundamental problem in network experiments is selecting an appropriate experimental
design in order to precisely estimate a given causal effect of interest. In fact, optimal rates of …
design in order to precisely estimate a given causal effect of interest. In fact, optimal rates of …
A Two-Part Machine Learning Approach to Characterizing Network Interference in A/B Testing
The reliability of controlled experiments, or" A/B tests," can often be compromised due to the
phenomenon of network interference, wherein the outcome for one unit is influenced by …
phenomenon of network interference, wherein the outcome for one unit is influenced by …