Two-sided exponential concentration bounds for Bayes error rate and Shannon entropy
We provide a method that approximates the Bayes error rate and the Shannon entropy with high probability. The Bayes error rate approximation makes possible to build a classifier that polynomially approaches Bayes error rate. The Shannon entropy approximation provides provable performance guarantees...
Main Authors: | Honorio, Jean (Contributor), Jaakkola, Tommi S. (Contributor) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor) |
Format: | Article |
Language: | English |
Published: |
Association for Computing Machinery (ACM),
2015-12-18T13:51:02Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Tight bounds for the expected risk of linear classifiers and PAC-bayes finite-sample guarantees
by: Honorio Carrillo, Jean, et al.
Published: (2018) -
New bounds for Shannon, Relative and Mandelbrot entropies via Hermite interpolating polynomial
by: Mehmood Nasir, et al.
Published: (2018-05-01) -
A Review of Shannon and Differential Entropy Rate Estimation
by: Andrew Feutrill, et al.
Published: (2021-08-01) -
Exponential bounds on error probability with Feedback
by: Nakiboḡlu, Bariş
Published: (2011) -
Shannon entropy and particle decays
by: Pedro Carrasco Millán, et al.
Published: (2018-05-01)