English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We investigate how to exploit structural similarities of an individual'spotential outcomes (POs) under different treatments to obtain better estimatesof conditional average treatment effects in finite samples. Especially when itis unknown whether a treatment has an effect at all, it is natural tohypothesize that the POs are similar - yet, some existing strategies fortreatment effect estimation employ regularization schemes that implicitlyencourage heterogeneity even when it does not exist and fail to fully make useof shared structure. In this paper, we investigate and compare three end-to-endlearning strategies to overcome this problem - based on regularization,reparametrization and a flexible multi-task architecture - each encodinginductive bias favoring shared behavior across POs. To build understanding oftheir relative strengths, we implement all strategies using neural networks andconduct a wide range of semi-synthetic experiments. We observe that all threeapproaches can lead to substantial improvements upon numerous baselines andgain insight into performance differences across various experimental settings.

On Inductive Biases for Heterogeneous Treatment Effect Estimation