AI Chat AI Image Generator AI Video Text to Speech

A More General Robust Loss Function

01/11/2017

∙

by Jonathan T. Barron, et al.

∙

∙

We present a two-parameter loss function which can be viewed as a generalization of many popular loss functions used in robust statistics: the Cauchy/Lorentzian, Geman-McClure, Welsch, and generalized Charbonnier loss functions (and by transitivity the L2, L1, L1-L2, and pseudo-Huber/Charbonnier loss functions). We describe and visualize this loss, and document several of its useful properties.

page 1

page 2

page 3

page 4

research

∙ 08/28/2021

Generalized Huber Loss for Robust Learning and its Efficient Minimization for a Robust Statistics

We propose a generalized formulation of the Huber loss. We show that wit...

0 Kaan Gokcesu, et al. ∙

research

∙ 09/15/2021

Generalized XGBoost Method

The XGBoost method has many advantages and is especially suitable for st...

0 Yang Guang, et al. ∙

research

∙ 05/11/2023

Adaptive Graduated Nonconvexity Loss

Many problems in robotics, such as estimating the state from noisy senso...

0 Kyungmin Jung, et al. ∙

research

∙ 11/17/2017

Wing Loss for Robust Facial Landmark Localisation with Convolutional Neural Networks

We present a new loss function, namely Wing loss, for robust facial land...

0 Zhen-Hua Feng, et al. ∙

research

∙ 01/13/2023

A survey and taxonomy of loss functions in machine learning

Most state-of-the-art machine learning techniques revolve around the opt...

0 Lorenzo Ciampiconi, et al. ∙

research

∙ 11/14/2017

Loss Functions for Multiset Prediction

We study the problem of multiset prediction. The goal of multiset predic...

0 Sean Welleck, et al. ∙

research

∙ 02/23/2023

The Geometry of Mixability

Mixable loss functions are of fundamental importance in the context of p...

0 Armando J. Cabrera Pacheco, et al. ∙