AI Chat AI Image Generator AI Video Text to Speech

A Bennett Inequality for the Missing Mass

03/20/2015

∙

by Bahman Yari Saeed Khanloo, et al.

∙

∙

Novel concentration inequalities are obtained for the missing mass, i.e. the total probability mass of the outcomes not observed in the sample. We derive distribution-free deviation bounds with sublinear exponents in deviation size for missing mass and improve the results of Berend and Kontorovich (2013) and Yari Saeed Khanloo and Haffari (2015) for small deviations which is the most important case in learning theory.

research

∙ 03/10/2015

Novel Bernstein-like Concentration Inequalities for the Missing Mass

We are concerned with obtaining novel concentration inequalities for the...

0 Bahman Yari Saeed Khanloo, et al. ∙

research

∙ 05/19/2020

Revisiting Concentration of Missing Mass

We revisit the problem of missing mass concentration, deriving Bernstein...

0 Maciej Skorski, et al. ∙

research

∙ 02/27/2019

Consistent estimation of the missing mass for feature models

Feature models are popular in machine learning and they have been recent...

0 Fadhel Ayed, et al. ∙

research

∙ 03/12/2015

On the Impossibility of Learning the Missing Mass

This paper shows that one cannot learn the probability of rare events wi...

0 Elchanan Mossel, et al. ∙

research

∙ 02/06/2022

Unnormalized Measures in Information Theory

Information theory is built on probability measures and by definition a ...

0 Peter Harremoes, et al. ∙

research

∙ 02/25/2014

Novel Deviation Bounds for Mixture of Independent Bernoulli Variables with Application to the Missing Mass

In this paper, we are concerned with obtaining distribution-free concent...

0 Bahman Yari Saeed Khanloo, et al. ∙

research

∙ 10/05/2021

Estimation and Concentration of Missing Mass of Functions of Discrete Probability Distributions

Given a positive function g from [0,1] to the reals, the function's miss...

0 Prafulla Chandra, et al. ∙