Constructing Multiclass Classifiers using Binary Classifiers Under Log-Loss

02/16/2021
by   Assaf Ben-Yishai, et al.
0

The construction of multiclass classifiers from binary classifiers is studied in this paper, and performance is quantified by the regret, defined with respect to the Bayes optimal log-loss. We start by proving that the regret of the well known One vs. All (OVA) method is upper bounded by the sum of the regrets of its constituent binary classifiers. We then present a new method called Conditional OVA (COVA), and prove that its regret is given by the weighted sum of the regrets corresponding to the constituent binary classifiers. Lastly, we present a method termed Leveraged COVA (LCOVA), designated to reduce the regret of a multiclass classifier by breaking it down to independently optimized binary classifiers.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/16/2019

Does the Multisecretary Problem Always Have Bounded Regret?

Arlotto and Gurvich (2019) showed that the regret in the multisecretary ...
research
01/28/2022

On the Kolmogorov Complexity of Binary Classifiers

We provide tight upper and lower bounds on the expected minimum Kolmogor...
research
09/08/2021

Sharp regret bounds for empirical Bayes and compound decision problems

We consider the classical problems of estimating the mean of an n-dimens...
research
07/27/2021

Statistical Guarantees for Fairness Aware Plug-In Algorithms

A plug-in algorithm to estimate Bayes Optimal Classifiers for fairness-a...
research
03/07/2018

Successive Wyner-Ziv Coding for the Binary CEO Problem under Log-Loss

An l-link binary CEO problem is considered in this paper. We present a p...
research
08/26/2023

Class Binarization to NeuroEvolution for Multiclass Classification

Multiclass classification is a fundamental and challenging task in machi...
research
02/05/2023

Revisiting Discriminative vs. Generative Classifiers: Theory and Implications

A large-scale deep model pre-trained on massive labeled or unlabeled dat...

Please sign up or login with your details

Forgot password? Click here to reset