Frame-based Data Factorizations

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

Archetypal Analysis is the method of choice to compute interpretable matrix factorizations. Every data point is represented as a convex combination of factors, i.e., points on the boundary of the convex hull of the data. This renders computation inefficient. In this paper, we show that the set of vertices of a convex hull, the so-called frame, can be efficiently computed by a quadratic program. We provide theoretical and empirical results for our proposed approach and make use of the frame to accelerate Archetypal Analysis. The novel method yields similar reconstruction errors as baseline competitors but is much faster to compute.
OriginalspracheEnglisch
Titel34th International Conference on Machine Learning, ICML 2017
HerausgeberDoina Precup, Yee Whye Teh
Anzahl der Seiten9
ErscheinungsortRed Hook
VerlagCurran Associates
Erscheinungsdatum25.07.2017
Seiten2305-2313
ISBN (elektronisch)978-1-5108-5514-4
PublikationsstatusErschienen - 25.07.2017
VeranstaltungInternational Conference on Machine Learning - ICML 2017: Thirty-fourth International Conference on Machine Learning - International Convention Centre, Sydney , Sydney, Australien
Dauer: 06.08.201711.08.2017
Konferenznummer: 34
https://icml.cc/Conferences/2017

Links

Zuletzt angesehen

Publikationen

  1. Gerbil – Benchmarking named entity recognition and linking consistently
  2. Introduction to the Design, Implementation, and Management of Digital Government Policies and Strategies Minitrack
  3. Strengthening the transformative impulse while mainstreaming real-world labs: Lessons learned from three years of BaWü-Labs
  4. Learning in the "Third Space"
  5. Introduction: Habitual Action, Automaticity, and Control
  6. Practice and carryover effects when using small interaction devices
  7. Teaching Sustainable Development in a Sensory and Artful Way — Concepts, Methods, and Examples
  8. Unraveling Privacy Concerns in Complex Data Ecosystems with Architectural Thinking
  9. Influence of Mg content in Al alloys on processing characteristics and dynamically recrystallized microstructure of friction surfacing deposits
  10. A Two-Stage Augmented Extended Kalman Filter as an Observer for Sensorless Valve Control in Camless Internal Combustion Engines
  11. Stimulating Computing
  12. Comparison of three methods of length compensation in a parallel kinematic and their equivalence conditions
  13. Introduction
  14. Can a Revision of the Universal Service Scope Result in Substantive Change?
  15. Modeling and simulation of the heterogenous material behavior in thermal-sprayed coatings
  16. Sliding Mode Control of an Inductive Power Transmission System with Maximum Efficiency
  17. Hybrid modelling by machine learning corrections of analytical model predictions towards high-fidelity simulation solutions
  18. Estimated substitution elasticities of a nested CES production function approach for Germany
  19. Short-arc measurement and fitting based on the bidirectional prediction of observed data
  20. Graph-Based Early-Fusion for Flood Detection
  21. Adaptive Notch Filter in Wavelet Packet Trees
  22. An introduction to sliding mode control for interdisciplinary education
  23. Short and long-term dominance of negative information in shaping public energy perceptions
  24. Deconstructing and reconstructing diversity in client-provider-relationships of social work
  25. Analysis of the relevance of models, influencing factors and the point in time of the forecast on the prediction quality in order-related delivery time determination using machine learning
  26. A Framework for Applying Natural Language Processing in Digital Health Interventions
  27. Vielfalt des Alterns - Differenz oder Integration?
  28. Changing the decision context to enable social learning for climate adaptation
  29. On the Equivalence of Transmission Problems in Nonoverlapping Domain Decomposition Methods for Quasilinear PDEs