We consider the estimation of heterogeneous treatment effects with arbitrary machine learning methods in the presence of unobserved confounders with the aid of a valid instrument. Such settings arise in A/B tests with an intent-to-treat structure, where the experimenter randomizes over which user will receive a recommendation to take an action, and we are interested in the effect of the downstream action. We develop a statistical learning approach to the estimation of heterogeneous effects, reducing the problem to the minimization of an appropriate loss function that depends on a set of auxiliary models (each corresponding to a separate prediction task). The reduction enables the use of all recent algorithmic advances (e.g.

The authors develop new algorithms for instrumental variables based on the orthogonal ML technique. The paper considers the IV problem in terms of moment conditions and derive conditions where the target quantity of interest has a good rate of estimation. Then the evaluation is done on a number of experimental settings on semi-synthetic and real data. The theoretical contributions could be better explained instead of purely linking it away to existing literature; please consider adding full consistency proof for completeness. It would also serve the reader if a larger discussion the original double ML work and neyman-orthogonality was included.

This paper solves an open problem, giving for the first time a provable method for efficiently using arbitrary ML algorithms for estimating heterogeneous effects in the instrumental variable scenario. Substantial experiments on several large datasets very nicely tie together theory to practice, in important and meaningful application areas. The reviewers have several proposal for making the paper clearer, which I trust the authors will follow. An important issue that must be clarified is the role of the monotonicity assumption given informally in the second paragraph of the paper.

We consider the estimation of heterogeneous treatment effects with arbitrary machine learning methods in the presence of unobserved confounders with the aid of a valid instrument. Such settings arise in A/B tests with an intent-to-treat structure, where the experimenter randomizes over which user will receive a recommendation to take an action, and we are interested in the effect of the downstream action. We develop a statistical learning approach to the estimation of heterogeneous effects, reducing the problem to the minimization of an appropriate loss function that depends on a set of auxiliary models (each corresponding to a separate prediction task). The reduction enables the use of all recent algorithmic advances (e.g. We show that the estimated effect model is robust to estimation errors in the auxiliary models, by showing that the loss satisfies a Neyman orthogonality criterion.

Airborne infectious diseases such as COVID-19 spread when healthy people are in close proximity to infected people. Technology-assisted methods to detect proximity in order to alert people are needed. In this work we systematically investigating Machine Learning (ML) methods to detect proximity by analyzing data gathered from smartphones' built-in Bluetooth, accelerometer and gyroscope sensors. We extracted 20 statistical features from raw sensor data, which were then classified ( 6ft or not) and regressed (distance estimate) using ML algorithms. We found that elliptical filtering of accelerometer and gyroscope sensors signal improved the performance of ML regression.

We consider the estimation of heterogeneous treatment effects with arbitrary machine learning methods in the presence of unobserved confounders with the aid of a valid instrument. Such settings arise in A/B tests with an intent-to-treat structure, where the experimenter randomizes over which user will receive a recommendation to take an action, and we are interested in the effect of the downstream action. We develop a statistical learning approach to the estimation of heterogeneous effects, reducing the problem to the minimization of an appropriate loss function that depends on a set of auxiliary models (each corresponding to a separate prediction task). The reduction enables the use of all recent algorithmic advances (e.g. We show that the estimated effect model is robust to estimation errors in the auxiliary models, by showing that the loss satisfies a Neyman orthogonality criterion.