Causal-Informed Hybrid Online Adaptive Optimization for Ad Load Personalization in Large-Scale Social Networks

TL;DR

This paper introduces a hybrid optimization framework combining primal-dual methods and Bayesian Optimization, enhanced with causal modeling, to efficiently personalize ad load in large social networks, balancing user experience and revenue.

Contribution

It presents a novel hybrid online adaptive optimization method that integrates causal inference with Bayesian Optimization and primal-dual techniques for large-scale ad personalization.

Findings

Faster convergence compared to traditional methods

Robust constraint satisfaction in dynamic environments

Improved personalization metrics in real-world tests

Abstract

Personalizing ad load in large-scale social networks requires balancing user experience and conversions under operational constraints. Traditional primal-dual methods enforce constraints reliably but adapt slowly in dynamic environments, while Bayesian Optimization (BO) enables exploration but suffers from slow convergence. We propose a hybrid online adaptive optimization framework CTRCBO ( Cohort-Based Trust Region Contextual Bayesian Optimization), combining primal-dual with BO, enhanced by trust-region updates and Gaussian Process Regression (GPR) surrogates for both objectives and constraints. Our approach leverages a upstream Causal ML model to inform the surrogate, improving decision quality and enabling efficient exploration-exploitation and online tuning. We evaluate our method on a billion-user social network, demonstrating faster convergence, robust constraint satisfaction, and improved personalization metrics, including real-world online AB test results.