Multiclass Learning with Simplex Coding

09/06/2012
by   Youssef Mroueh, et al.
0

In this paper we discuss a novel framework for multiclass learning, defined by a suitable coding/decoding strategy, namely the simplex coding, that allows to generalize to multiple classes a relaxation approach commonly used in binary classification. In this framework, a relaxation error analysis can be developed avoiding constraints on the considered hypotheses class. Moreover, we show that in this setting it is possible to derive the first provably consistent regularized method with training/tuning complexity which is independent to the number of classes. Tools from convex analysis are introduced that can be used beyond the scope of this paper.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/03/2022

Generalization for multiclass classification with overparameterized linear models

Via an overparameterized linear model with Gaussian features, we provide...
research
08/25/2019

LightMC: A Dynamic and Efficient Multiclass Decomposition Algorithm

Multiclass decomposition splits a multiclass classification problem into...
research
08/16/2019

Convex geometry of the Coding problem for error constrained Dictionary Learning

In this article we expose the convex geometry of the class of coding pro...
research
11/27/2019

Alternative Metrics

The main scope of this chapter is metrics defined for coding and decodin...
research
07/05/2021

Performance Analysis of Regularized Convex Relaxation for Complex-Valued Data Detection (Extended Version)

In this work, we study complex-valued data detection performance in mass...
research
03/08/2017

Don't Fear the Bit Flips: Optimized Coding Strategies for Binary Classification

After being trained, classifiers must often operate on data that has bee...
research
09/01/2016

A Novel Progressive Learning Technique for Multi-class Classification

In this paper, a progressive learning technique for multi-class classifi...

Please sign up or login with your details

Forgot password? Click here to reset