Abstract | ||
---|---|---|
In high-dimensional classification or regression problems, the expected gradient outerproduct (EGOP) of the unknown regression function f, namely E-x (del f(X). del f(X)(T)), is known to recover those directions v is an element of R-d most relevant to predicting the output Y.However, just as in gradient estimation, optimal estimators of the EGOP can be expensive in practice. We show that a simple rough estimator, much cheaper in practice, suffices to obtain significant improvements on real-world nonparametric classification and regression tasks. Furthermore, we prove that, despite its simplicity, this rough estimator remains statistically consistent under mild conditions. |
Year | Venue | Field |
---|---|---|
2014 | UNCERTAINTY IN ARTIFICIAL INTELLIGENCE | Regression function,Mathematical optimization,Nonparametric classification,Regression,Regression problems,Statistics,Mathematics,Estimator,Gradient estimation,Consistent estimator |
DocType | Citations | PageRank |
Conference | 2 | 0.39 |
References | Authors | |
4 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shubhendu Trivedi | 1 | 76 | 7.66 |
Jialei Wang | 2 | 77 | 10.29 |
Samory Kpotufe | 3 | 92 | 11.56 |
Gregory Shakhnarovich | 4 | 1579 | 106.33 |