Rare Probability Estimation under Regularly Varying Heavy Tails
This paper studies the problem of estimating the probability of symbols that have occurred very rarely, in samples drawn independently from an unknown, possibly infinite, discrete distribution. In particular, we study the multiplicative consistency of estimators, defined as the ratio of the estimate...
Main Authors: | Ohannessian, Mesrob I., Dahleh, Munther A. |
---|---|
Other Authors: | Massachusetts Institute of Technology. Institute for Data, Systems, and Society |
Format: | Article |
Language: | en_US |
Published: |
Journal of Machine Learning Research
2015
|
Online Access: | http://hdl.handle.net/1721.1/99945 https://orcid.org/0000-0002-1470-2148 |
Similar Items
-
Large alphabets: Finite, infinite, and scaling models
by: Ohannessian, Mesrob I., et al.
Published: (2014) -
On inference about rare events
by: Ohannessian, Mesrob I., 1981-
Published: (2012) -
Simulation and visualization of fields and energy flows in electric circuits with idealized geometries
by: Ohannessian, Mesrob I., 1981-
Published: (2006) -
Estimation of ruin probability for heavy-tailed and light-tailed distribution in medical insurance /
by: Syahirah Saupi, 1994-, et al.
Published: (2016) -
On the Impossibility of Learning the Missing Mass
by: Ohannessian, Mesrob I., et al.
Published: (2019)