A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Experts

Hugo Inzirillo and Rémi Genet
Additional contact information
Hugo Inzirillo: CREST - Centre de Recherche en Économie et Statistique - ENSAI - Ecole Nationale de la Statistique et de l'Analyse de l'Information [Bruz] - X - École polytechnique - IP Paris - Institut Polytechnique de Paris - ENSAE Paris - École Nationale de la Statistique et de l'Administration Économique - IP Paris - Institut Polytechnique de Paris - CNRS - Centre National de la Recherche Scientifique
Rémi Genet: DRM - Dauphine Recherches en Management - Université Paris Dauphine-PSL - PSL - Université Paris Sciences et Lettres - CNRS - Centre National de la Recherche Scientifique

Working Papers from HAL

Abstract: This paper introduces KAMoE, a novel Mixture of Experts (MoE) framework based on Gated Residual KolmogorovArnold Networks (GRKAN). We propose GRKAN as an alternative to the traditional gating function, aiming to enhance efficiency and interpretability in MoE modeling. Through extensive experiments on digital asset markets and real estate valuation, wedemonstrate that KAMoE consistently outperforms traditional MoE architectures across various tasks and model types. Our results show that GRKAN exhibits superior performance compared to standard Gating Residual Networks, particularly in LSTMbased models for sequential tasks. We also provide insights into the trade-offs between model complexity and performance gains in MoE and KAMoE architectures.

Keywords: Machine Learning; Neural and Evolutionary Computing (search for similar items in EconPapers)
Date: 2025-02-01
Note: View the original document on HAL open archive server: https://hal.science/hal-04923946v1
References: Add references at CitEc
Citations:

Downloads: (external link)
https://hal.science/hal-04923946v1/document (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:hal:wpaper:hal-04923946

Access Statistics for this paper

More papers in Working Papers from HAL
Bibliographic data for series maintained by CCSD ().