Name
Title | ||
|---|---|---|
The k-Nearest Representatives Classifier: A Distance-Based Classifier with Strong Generalization Bounds |
Abstract | ||
|---|---|---|
We define the k-Nearest Representatives (k-NR) classifier, a distance-based classifier similar to the k-nearest neighbors classifier with comparable accuracy in practice, and stronger generalization bounds. Uniform convergence is shown through Rademacher complexity, and generalizability is controlled through regularization. Finite-sample risk bound are also given. Compared to the k-NN, the k-NR requires less memory to store and classification queries may be made more efficiently. Training is also efficient, being polynomial in all parameters, and is accomplished via a simple empirical risk minimization process. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/DSAA.2017.22 | 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA) |
Keywords | Field | DocType |
Classification,Statistical Learning Theory,Rademacher Complexity,VC Dimension,Nearest Neighbor,Quantization,Regularization,Empirical Risk Minimization | Convergence (routing),Generalizability theory,Polynomial,Computer science,Empirical risk minimization,Rademacher complexity,Algorithm,Uniform convergence,Regularization (mathematics),Classifier (linguistics) | Conference |
ISSN | ISBN | Citations |
2472-1573 | 978-1-5090-5005-5 | 0 |
PageRank | References | Authors |
0.34 | 6 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Cyrus Cousins | 1 | 0 | 5.41 |
| Eli Upfal | 2 | 4310 | 743.13 |