On Classification-Calibration of Gamma-Phi Losses

02/14/2023
by   Yutong Wang, et al.
0

Gamma-Phi losses constitute a family of multiclass classification loss functions that generalize the logistic and other common losses, and have found application in the boosting literature. We establish the first general sufficient condition for the classification-calibration of such losses. In addition, we show that a previously proposed sufficient condition is in fact not sufficient.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/30/2019

On the Consistency of Top-k Surrogate Losses

The top-k error is often employed to evaluate performance for challengin...
research
09/20/2016

Multiclass Classification Calibration Functions

In this paper we refine the process of computing calibration functions f...
research
01/27/2019

On Symmetric Losses for Learning from Corrupted Labels

This paper aims to provide a better understanding of a symmetric loss. F...
research
01/30/2019

On Possibility and Impossibility of Multiclass Classification with Rejection

We investigate the problem of multiclass classification with rejection, ...
research
05/02/2022

Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators

We present incomplete gamma kernels, a generalization of Locally Optimal...
research
05/19/2022

Learning Energy Networks with Generalized Fenchel-Young Losses

Energy-based models, a.k.a. energy networks, perform inference by optimi...
research
07/18/2022

Rank-based Decomposable Losses in Machine Learning: A Survey

Recent works have revealed an essential paradigm in designing loss funct...

Please sign up or login with your details

Forgot password? Click here to reset