Fitting aggregation functions to data: Part I-Linearization and regularization
Maciej Bartoszuk , Gleb Beliakov , Marek Gągolewski , Simon James
AbstractThe use of supervised learning techniques for fitting weights and/or generator functions of weighted quasi-arithmetic means – a special class of idempotent and nondecreasing aggregation functions – to empirical data has already been considered in a number of papers. Nevertheless, there are still some important issues that have not been discussed in the literature yet. In the first part of this two-part contribution we deal with the concept of regularization, a quite standard technique from machine learning applied so as to increase the fit quality on test and validation data samples. Due to the constraints on the weighting vector, it turns out that quite different methods can be used in the current framework, as compared to regression models. Moreover, it is worth noting that so far fitting weighted quasi-arithmetic means to empirical data has only been performed approximately, via the so-called linearization technique. In this paper we consider exact solutions to such special optimization tasks and indicate cases where linearization leads to much worse solutions.
|Publication size in sheets||0.6|
|Book||Carvalho Joao Paulo, Lesot Marie-Jeanne, Kaymak Uzay, Vieira Susana, Bouchon-Meunier Bernadette, Yager Ronald R. (eds.): INFORMATION PROCESSING AND MANAGEMENT OF UNCERTAINTY IN KNOWLEDGE-BASED SYSTEMS, IPMU 2016, PT II, Communications in Computer and Information Science, vol. 611, 2016, SPRINGER INT PUBLISHING AG, ISBN 978-3-319-40581-0, [ 978-3-319-40580-3]|
|Keywords in English||Aggregation functions; Weighted quasi-arithmetic means; Least squares fitting; Regularization; Linearization|
|Score|| = 15.0, 04-09-2019, BookChapterSeriesAndMatConfByConferenceseries|
= 15.0, 04-09-2019, BookChapterSeriesAndMatConfByConferenceseries
|Publication indicators||= 4; : 2016 = 0.317|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.