Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Algorithms  /  Vol: 16 Par: 5 (2023)  /  Artículo
ARTÍCULO
TITULO

Heterogeneous Treatment Effect with Trained Kernels of the Nadaraya?Watson Regression

Andrei Konstantinov    
Stanislav Kirpichenko and Lev Utkin    

Resumen

A new method for estimating the conditional average treatment effect is proposed in this paper. It is called TNW-CATE (the Trainable Nadaraya?Watson regression for CATE) and based on the assumption that the number of controls is rather large and the number of treatments is small. TNW-CATE uses the Nadaraya?Watson regression for predicting outcomes of patients from control and treatment groups. The main idea behind TNW-CATE is to train kernels of the Nadaraya?Watson regression by using a weight sharing neural network of a specific form. The network is trained on controls, and it replaces standard kernels with a set of neural subnetworks with shared parameters such that every subnetwork implements the trainable kernel, but the whole network implements the Nadaraya?Watson estimator. The network memorizes how the feature vectors are located in the feature space. The proposed approach is similar to transfer learning when domains of source and target data are similar, but the tasks are different. Various numerical simulation experiments illustrate TNW-CATE and compare it with the well-known T-learner, S-learner, and X-learner for several types of control and treatment outcome functions. The code of proposed algorithms implementing TNW-CATE is publicly available.

 Artículos similares

       
 
Gayathri Anil, Jaimy Scaria and Puthiya Veetil Nidheesh    
In the present study, heterogeneous electro-Fenton (HEF) process using MnFe2O4-GO catalyst is employed for the successful removal of dye from aqueous solution. Pt coated over titanium and graphite felt were used as the electrodes. The study focuses on th... ver más
Revista: Water

 
Shigeru Obayashi and Hirotaka Saito    
Neuromodulators at the periphery, such as neuromuscular electrical stimulation (NMES), have been developed as add-on tools to regain upper extremity (UE) paresis after stroke, but this recovery has often been limited. To overcome these limits, novel stra... ver más
Revista: Applied Sciences

 
Carolina Rodríguez, Bárbara García, Caterin Pinto, Rafael Sánchez, Jennyfer Serrano and Eduardo Leiva    
Water scarcity is a problem of global relevance that is affecting more and more people in the world. Latin America and the Caribbean (LAC) have around 35% of the world?s renewable water resources. However, the management of water resources and inequality... ver más
Revista: Water

 
Chao-Ching Chiang, Philip Nathaniel Immanuel, Yi-Hsiung Chiu and Song-Jeng Huang    
In this work we report on a rapid, easy-to-operate, lossless, room temperature heterogeneous H2O plasma treatment process for the bonding of poly(methyl methacrylate) (PMMA) and double-sided polished (DSP) silicon substrates by for utilization in sandwic... ver más
Revista: Coatings

 
Bahareh Montazeri, Olga Koba-Ucun, Idil Arslan-Alaton and Tugba Olmez-Hanci    
The degradation of iprodione (IPR), a once frequently used but recently banned dicarboximide fungicide, by UV-C light-, zero-valent iron- (ZVI), and zero-valent aluminium (ZVA)-activated persulfate (PS) oxidation processes was comparatively studied in di... ver más
Revista: Water