@InProceedings{FrochteMarsland2019,
author="Frochte, J{\"o}rg
and Marsland, Stephen",
editor="Le, Thuc D.
and Ong, Kok-Leong
and Zhao, Yanchang
and Jin, Warren H.
and Wong, Sebastien
and Liu, Lin
and Williams, Graham",
title="A Learning Approach for Ill-Posed Optimisation Problems",
booktitle="Data Mining",
year="2019",
publisher="Springer Singapore",
address="Singapore",
pages="16--27",
abstract="Supervised learning can be thought of as finding a mapping between spaces of input and output vectors. In the case that the function to be learned is multi-valued (so that there are several correct output values for a given input) the problem becomes ill-posed, and many standard methods fail to find good solutions. However, optimisation problems based on multi-valued functions are relatively common. They include reverse robot kinematics, and the research field of AutoML -- which is becoming increasingly popular -- where one seeks to establish optimal hyperparameters for a learning algorithm for a particular problem based on loss function values for trained networks, or to reuse training from previous networks. We present an analysis of this problem, together with an approach based on k-nearest neighbours, which we demonstrate on a set of simple examples, including two application areas of interest.",
isbn="978-981-15-1699-3"
}