S
Sören R. Künzel
Researcher at University of California, Berkeley
Publications - 9
Citations - 646
Sören R. Künzel is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Estimator & Blazar. The author has an hindex of 5, co-authored 9 publications receiving 336 citations. Previous affiliations of Sören R. Künzel include Yale University.
Papers
More filters
Journal ArticleDOI
Metalearners for estimating heterogeneous treatment effects using machine learning
TL;DR: A metalearner, the X-learner, is proposed, which can adapt to structural properties, such as the smoothness and sparsity of the underlying treatment effect, and is shown to be easy to use and to produce results that are interpretable.
Journal ArticleDOI
A COMPREHENSIVE STATISTICAL DESCRIPTION OF RADIO-THROUGH-γ-RAY SPECTRAL ENERGY DISTRIBUTIONS OF ALL KNOWN BLAZARS
Peiyuan Mao,C. Megan Urry,Francesco Massaro,Francesco Massaro,Francesco Massaro,Alessandro Paggi,Joe Cauteruccio,Sören R. Künzel +7 more
Posted Content
Transfer Learning for Estimating Causal Effects using Neural Networks
Sören R. Künzel,Bradly C. Stadie,Nikita Vemuri,Varsha Ramakrishnan,Jasjeet S. Sekhon,Pieter Abbeel +5 more
TL;DR: New algorithms for estimating heterogeneous treatment effects, combining recent developments in transfer learning for neural networks with insights from the causal inference literature are developed, which can perform an order of magnitude better than existing benchmarks while using a fraction of the data.
Posted Content
Causaltoolbox---Estimator Stability for Heterogeneous Treatment Effects
TL;DR: In this paper, a variety of procedures relying on different assumptions have been suggested for estimating heterogeneous treatment effects, and the conclusion of many published papers might change had a different estimator been chosen and suggest that practitioners should evaluate many estimators and assess their similarity when investigating heterogenous treatment effects.
Posted Content
Linear Aggregation in Tree-based Estimators
TL;DR: A new algorithm is introduced which finds the best axis-aligned split to fit optimal linear aggregation functions on the corresponding nodes and implement this method in the provably fastest way, enabling to create more interpretable trees and obtain better predictive performance on a wide range of data sets.