AI Chat AI Image Generator AI Video Text to Speech

On the Kolmogorov Complexity of Binary Classifiers

01/28/2022

∙

by Samuel Epstein, et al.

∙

∙

We provide tight upper and lower bounds on the expected minimum Kolmogorov complexity of binary classifiers that are consistent with labeled samples. The expected size is not more than complexity of the target concept plus the conditional entropy of the labels given the sample.

page 1

page 2

page 3

page 4

research

∙ 12/26/2021

The Sketching and Communication Complexity of Subsequence Detection

We study the sketching and communication complexity of deciding whether ...

0 Mason DiCicco, et al. ∙

research

∙ 07/30/2020

Determination of 2-Adic Complexity of Generalized Binary Sequences of Order 2

The generalized binary sequences of order 2 have been used to construct ...

0 Minghui Yang, et al. ∙

research

∙ 02/16/2021

Constructing Multiclass Classifiers using Binary Classifiers Under Log-Loss

The construction of multiclass classifiers from binary classifiers is st...

0 Assaf Ben-Yishai, et al. ∙

research

∙ 03/11/2013

Refinement revisited with connections to Bayes error, conditional entropy and calibrated classifiers

The concept of refinement from probability elicitation is considered for...

0 Hamed Masnadi-Shirazi, et al. ∙

research

∙ 07/10/2019

On the Complexity of Completing Binary Predicates

Given a binary predicate P, the length of the smallest program that comp...

0 Samuel Epstein, et al. ∙

research

∙ 10/01/2019

The Minimization of Random Hypergraphs

We investigate the maximum-entropy model B_n,m,p for random n-vertex, m-...

0 Thomas Bläsius, et al. ∙

research

∙ 05/11/2016

Asymptotic sequential Rademacher complexity of a finite function class

For a finite function class we describe the large sample limit of the se...

0 Dmitry B. Rokhlin, et al. ∙