Efficient and accurate ℓ p-norm multiple kernel learning

Research output: Contributions to collected editions/worksArticle in conference proceedingsResearchpeer-review

Authors

  • Marius Kloft
  • Ulf Brefeld
  • Soren Sonnenburg
  • Pavel Laskov
  • Klaus Robert Müller
  • Alexander Zien

Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability. Unfortunately, ℓ 1-norm MKL is hardly observed to outperform trivial baselines in practical applications. To allow for robust kernel mixtures, we generalize MKL to arbitrary ℓ p-norms. We devise new insights on the connection between several existing MKL formulations and develop two efficient interleaved optimization strategies for arbitrary p > 1. Empirically, we demonstrate that the interleaved optimization strategies are much faster compared to the traditionally used wrapper approaches. Finally, we apply ℓp-norm MKL to real-world problems from computational biology, showing that non-sparse MKL achieves accuracies that go beyond the state-of-the-art.

Original languageEnglish
Title of host publicationAdvances in Neural Information Processing Systems 22 : Proceedings of the 23rd Annual Conference on Neural Information Processing Systems 2009
EditorsYoshua Bengio, Dale Schuurmans, John Lafferty, Chris Williams, Aron Culotta
Number of pages9
PublisherNeural Information Processing Systems
Publication date2009
Pages997-1005
ISBN (print)978-161567911-9
Publication statusPublished - 2009
Externally publishedYes
Event23rd Annual Conference on Neural Information Processing Systems, NIPS 2009 - Hyatt Regency Vancouver, Vancouver, BC, Canada
Duration: 07.12.200910.12.2009
Conference number: 23
https://nips.cc/Conferences/2009

Recently viewed

Publications

  1. Neural network-based adaptive fault-tolerant control for strict-feedback nonlinear systems with input dead zone and saturation
  2. Different complex word problems require different combinations of cognitive skills
  3. Semantic Parsing for Knowledge Graph Question Answering with Large Language Models
  4. Control of the inverse pendulum based on sliding mode and model predictive control
  5. Clustering Hydrological Homogeneous Regions and Neural Network Based Index Flood Estimation for Ungauged Catchments
  6. Latent structure perceptron with feature induction for unrestricted coreference resolution
  7. Selecting and Adapting Methods for Analysis and Design in Value-Sensitive Digital Social Innovation Projects: Toward Design Principles
  8. Modeling Effective and Ineffective Knowledge Communication and Learning Discourses in CSCL with Hidden Markov Models
  9. Problem structuring for transitions
  10. Using Decision Trees and Reinforcement Learning for the Dynamic Adjustment of Composite Sequencing Rules in a Flexible Manufacturing System
  11. Spatial mislocalization as a consequence of sequential coding of stimuli
  12. DialogueMaps: Supporting interactive transdisciplinary dialogues with a web-based tool for multi-layer knowledge maps
  13. Real-time RDF extraction from unstructured data streams
  14. A Multivariate Method for Dynamic System Analysis
  15. On the Decoupling and Output Functional Controllability of Robotic Manipulation
  16. Analysis of long-term statistical data of cobalt flows in the EU
  17. Supporting the Development and Implementation of a Digitalization Strategy in SMEs through a Lightweight Architecture-based Method
  18. FFTSMC with Optimal Reference Trajectory Generated by MPC in Robust Robotino Motion Planning with Saturating Inputs
  19. Retest effects in matrix test performance