Non-Linear Counterfactual Aggregate Optimization
By: Benjamin Heymann, Otmane Sakhi
Potential Business Impact:
Improves online tests to find best results faster.
We consider the problem of directly optimizing a non-linear function of an outcome, where this outcome itself is the sum of many small contributions. The non-linearity of the function means that the problem is not equivalent to the maximization of the expectation of the individual contribution. By leveraging the concentration properties of the sum of individual outcomes, we derive a scalable descent algorithm that directly optimizes for our stated objective. This allows for instance to maximize the probability of successful A/B test, for which it can be wiser to target a success criterion, such as exceeding a given uplift, rather than chasing the highest expected payoff.
Similar Papers
Non-Linear Model-Based Sequential Decision-Making in Agriculture
Machine Learning (Stat)
Helps farmers use less fertilizer for better crops.
Computing Strategic Responses to Non-Linear Classifiers
Machine Learning (CS)
Helps computers learn when people try to trick them.
Heterogeneous Causal Learning for Optimizing Aggregated Functions in User Growth
Machine Learning (CS)
Finds best customers, saves money on ads.