Gradient Weights help Nonparametric Regressors

By Samory Kpotufe, Abdeslam Boularias. 2012

8 citations recorded by the source corpus.

Subfields: Statistics and Probability, Statistical Learning Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistics and Probability

1. David Balduzzi
2. Muhammad Ghifary
3. Jialei Wang
4. Shubhendu Trivedi
5. Gregory Shakhnarovich
6. Samory Kpotufe
7. Barnab'as P'oczos
8. Ann B. Lee

In Statistical Learning Theory

1. David Balduzzi
2. Muhammad Ghifary
3. Jialei Wang
4. Shubhendu Trivedi
5. Gregory Shakhnarovich
6. Samory Kpotufe
7. Risi Kondor
8. Barnab'as P'oczos

Citations in the corpus

• Compatible Value Gradients for Reinforcement Learning of Continuous Deep Policies (2015, methodology): “Remarkably, GProp is competitive with fully-supervised nonparametric regression algorithms on the SARCOS and Barrett datasets, see Figure 2bc in (Nguyen-Tuong et al., 2008) and the results in (Kpotufe and Boularias, 2013; Trivedi et al., 2014).”
• A Consistent Estimator of the Expected Gradient Outerproduct (2014, methodology): “However [6] is only concerned with a variable selection setting where each coordinate i of X is to be weighted by an estimate of EX |f ′ i(X)|, which is their quantity of interest.”