A Unifying View of Representer Theorems

Authors: Andreas Argyriou, Francesco Dinuzzo

ICML 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper we propose a unified view, which generalizes the concept of representer theorems and extends necessary and sufficient conditions for such theorems to hold. Our main result shows a close connection between representer theorems and certain classes of regularization penalties, which we call orthomonotone functions. This result not only subsumes previous representer theorems as special cases but also yields a new class of optimality conditions, which goes beyond the classical linear combination of the data.
Researcher Affiliation Collaboration Andreas Argyriou ARGYRIOUA@ECP.FR Ecole Centrale Paris, Center for Visual Computing Francesco Dinuzzo FRANCESD@IE.IBM.COM IBM Research, Dublin and Max Planck Institute for Intelligent Systems, T ubingen
Pseudocode No The paper is highly theoretical and mathematical, focusing on definitions, theorems, and proofs. It does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating the availability of open-source code for the methodology described.
Open Datasets No The paper is theoretical and discusses mathematical frameworks and examples (e.g., RKHS, matrix regularization) without performing empirical experiments on specific datasets. Therefore, no information about publicly available datasets for training is provided.
Dataset Splits No The paper is theoretical and does not describe empirical experiments with dataset splits. Therefore, no information about training/test/validation dataset splits is provided.
Hardware Specification No The paper is theoretical and focuses on mathematical concepts. It does not describe any computational experiments or the hardware used to run them.
Software Dependencies No The paper is theoretical and focuses on mathematical concepts. It does not describe any computational experiments or the software dependencies required.
Experiment Setup No The paper is theoretical and focuses on mathematical concepts. It does not describe any experimental setup, hyperparameters, or system-level training settings.