Multi-Instance Learning with Any Hypothesis Class

07/11/2011
by   Sivan Sabato, et al.
0

In the supervised learning setting termed Multiple-Instance Learning (MIL), the examples are bags of instances, and the bag label is a function of the labels of its instances. Typically, this function is the Boolean OR. The learner observes a sample of bags and the bag labels, but not the instance labels that determine the bag labels. The learner is then required to emit a classification rule for bags based on the sample. MIL has numerous applications, and many heuristic algorithms have been used successfully on this problem, each adapted to specific settings or applications. In this work we provide a unified theoretical analysis for MIL, which holds for any underlying hypothesis class, regardless of a specific application or problem domain. We show that the sample complexity of MIL is only poly-logarithmically dependent on the size of the bag, for any underlying hypothesis class. In addition, we introduce a new PAC-learning algorithm for MIL, which uses a regular supervised learning algorithm as an oracle. We prove that efficient PAC-learning for MIL can be generated from any efficient non-MIL supervised learning algorithm that handles one-sided error. The computational complexity of the resulting algorithm is only polynomially dependent on the bag size.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/11/2022

A Characterization of Semi-Supervised Adversarially-Robust PAC Learnability

We study the problem of semi-supervised learning of an adversarially-rob...
research
03/28/2023

Learnability, Sample Complexity, and Hypothesis Class Complexity for Regression Models

The goal of a learning algorithm is to receive a training data set as in...
research
10/26/2018

Learning and Interpreting Multi-Multi-Instance Learning Networks

We introduce an extension of the multi-instance learning problem where e...
research
05/31/2020

Theory and Algorithms for Shapelet-based Multiple-Instance Learning

We propose a new formulation of Multiple-Instance Learning (MIL), in whi...
research
02/13/2019

Stable multi-instance learning visa causal inference

Multi-instance learning (MIL) deals with tasks where each example is rep...
research
08/18/2020

When Hardness of Approximation Meets Hardness of Learning

A supervised learning algorithm has access to a distribution of labeled ...
research
02/06/2023

Easy Learning from Label Proportions

We consider the problem of Learning from Label Proportions (LLP), a weak...

Please sign up or login with your details

Forgot password? Click here to reset