eprintid: 1517412 rev_number: 19 eprint_status: archive userid: 608 dir: disk0/01/51/74/12 datestamp: 2016-09-26 01:10:29 lastmod: 2020-02-12 18:56:11 status_changed: 2017-09-04 16:10:57 type: article metadata_visibility: show creators_name: Király, FJ creators_name: Kreuzer, M creators_name: Theran, L title: Dual-to-kernel learning with ideals ispublished: pub divisions: UCL divisions: A01 divisions: B04 divisions: C06 divisions: F61 keywords: Machine Learning (stat.ML); Learning (cs.LG); Commutative Algebra (math.AC); Algebraic Geometry (math.AG); Statistics Theory (math.ST) note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. abstract: In this paper, we propose a theory which unifies kernel learning and symbolic algebraic methods. We show that both worlds are inherently dual to each other, and we use this duality to combine the structure-awareness of algebraic methods with the efficiency and generality of kernels. The main idea lies in relating polynomial rings to feature space, and ideals to manifolds, then exploiting this generative-discriminative duality on kernel matrices. We illustrate this by proposing two algorithms, IPCA and AVICA, for simultaneous manifold and feature learning, and test their accuracy on synthetic and real world data. date: 2014-02-01 official_url: https://arxiv.org/abs/1402.0099 oa_status: green full_text_type: other language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1002722 lyricists_name: Kiraly, Franz lyricists_id: FJKIR17 full_text_status: public publication: arXiv.org article_number: arXiv:1402.0099 [stat.ML] citation: Király, FJ; Kreuzer, M; Theran, L; (2014) Dual-to-kernel learning with ideals. arXiv.org , Article arXiv:1402.0099 [stat.ML]. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/1517412/1/Kiraly_1402.0099v1.pdf