A short note on learning discrete distributions

02/25/2020
by   Clément L. Canonne, et al.
0

The goal of this short note is to provide simple proofs for the "folklore facts" on the sample complexity of learning a discrete probability distribution over a known domain of size k to various distances ε, with error probability δ.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/06/2022

Comments on "Testing Conditional Independence of Discrete Distributions"

In this short note, we identify and address an error in the proof of The...
research
02/26/2020

Decidability of Sample Complexity of PAC Learning in finite setting

In this short note we observe that the sample complexity of PAC machine ...
research
12/05/2018

A Short Note on the Jensen-Shannon Divergence between Simple Mixture Distributions

This short note presents results about the symmetric Jensen-Shannon dive...
research
11/09/2021

Complexity of the Ackermann fragment with one leading existential quantifier

In this short note we prove that the satisfiability problem of the Acker...
research
12/12/2012

Factorization of Discrete Probability Distributions

We formulate necessary and sufficient conditions for an arbitrary discre...
research
06/08/2018

The Saturated Subpaths Decomposition in Z 2 : a short note on generalized Tangential Cover

In this short note, we generalized the Tangential Cover used in Digital ...
research
09/30/2009

Algorithms for finding dispensable variables

This short note reviews briefly three algorithms for finding the set of ...

Please sign up or login with your details

Forgot password? Click here to reset