Local Rademacher Complexity for Multi-label Learning

10/26/2014
by   Chang Xu, et al.
0

We analyze the local Rademacher complexity of empirical risk minimization (ERM)-based multi-label learning algorithms, and in doing so propose a new algorithm for multi-label learning. Rather than using the trace norm to regularize the multi-label predictor, we instead minimize the tail sum of the singular values of the predictor in multi-label learning. Benefiting from the use of the local Rademacher complexity, our algorithm, therefore, has a sharper generalization error bound and a faster convergence rate. Compared to methods that minimize over all singular values, concentrating on the tail singular values results in better recovery of the low-rank structure of the multi-label predictor, which plays an import role in exploiting label correlations. We propose a new conditional singular value thresholding algorithm to solve the resulting objective function. Empirical studies on real-world datasets validate our theoretical results and demonstrate the effectiveness of the proposed algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/27/2017

Similarity-based Multi-label Learning

Multi-label classification is an important learning problem with many ap...
research
04/04/2017

Multi-Label Learning with Global and Local Label Correlation

It is well-known that exploiting label correlations is important to mult...
research
01/25/2017

Privileged Multi-label Learning

This paper presents privileged multi-label learning (PrML) to explore an...
research
10/08/2019

Self-Paced Multi-Label Learning with Diversity

The major challenge of learning from multi-label data has arisen from th...
research
08/03/2023

Exploiting Multi-Label Correlation in Label Distribution Learning

Label Distribution Learning (LDL) is a novel machine learning paradigm t...
research
12/17/2020

Characterizing the Evasion Attackability of Multi-label Classifiers

Evasion attack in multi-label learning systems is an interesting, widely...
research
07/27/2017

Food Ingredients Recognition through Multi-label Learning

Automatically constructing a food diary that tracks the ingredients cons...

Please sign up or login with your details

Forgot password? Click here to reset