Learning Bounds for Open-Set Learning

06/30/2021
by   Zhen Fang, et al.
6

Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. In this paper, we target a more challenging and realistic setting: open-set learning (OSL), where there exist test samples from the classes that are unseen during training. Although researchers have designed many methods from the algorithmic perspectives, there are few methods that provide generalization guarantees on their ability to achieve consistent performance on different training samples drawn from the same distribution. Motivated by the transfer learning and probably approximate correct (PAC) theory, we make a bold attempt to study OSL by proving its generalization error-given training samples with size n, the estimation error will get close to order O_p(1/√(n)). This is the first study to provide a generalization bound for OSL, which we do by theoretically investigating the risk of the target classifier on unknown classes. According to our theory, a novel algorithm, called auxiliary open-set risk (AOSR) is proposed to address the OSL problem. Experiments verify the efficacy of AOSR. The code is available at github.com/Anjin-Liu/Openset_Learning_AOSR.

READ FULL TEXT

page 32

page 33

research
03/24/2022

Open-set Recognition via Augmentation-based Similarity Learning

The primary assumption of conventional supervised learning or classifica...
research
10/26/2022

Is Out-of-Distribution Detection Learnable?

Supervised learning aims to train a classifier under the assumption that...
research
11/11/2020

EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labels

The efficacy of deep learning depends on large-scale data sets that have...
research
11/17/2020

Close Category Generalization

Out-of-distribution generalization is a core challenge in machine learni...
research
08/18/2023

Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization

Domain generalization (DG) is proposed to deal with the issue of domain ...
research
07/11/2019

Minimizers of the Empirical Risk and Risk Monotonicity

Plotting a learner's average performance against the number of training ...
research
01/14/2020

Unsupervised Learning of the Set of Local Maxima

This paper describes a new form of unsupervised learning, whose input is...

Please sign up or login with your details

Forgot password? Click here to reset