Efficient co-regularised least squares regression

Publikation: Beiträge in SammelwerkenAufsätze in KonferenzbändenForschungbegutachtet

Authors

In many applications, unlabelled examples are inexpensive and easy to obtain. Semi-supervised approaches try to utilise such examples to reduce the predictive error. In this paper, we investigate a semi-supervised least squares regression algorithm based on the co-learning approach. Similar to other semi-supervised algorithms, our base algorithm has cubic runtime complexity in the number of unlabelled examples. To be able to handle larger sets of unlabelled examples, we devise a semi-parametric variant that scales linearly in the number of unlabelled examples. Ex-periments show a significant error reduction by co-regularisation and a large runtime improvement for the semi-parametric approximation. Last but not least, we propose a distributed procedure that can be applied without collecting all data at a single site.

OriginalspracheEnglisch
TitelProceedings of the 23rd international conference on Machine learning
HerausgeberWilliam Cohen
Anzahl der Seiten8
VerlagAssociation for Computing Machinery, Inc
Erscheinungsdatum01.01.2006
Seiten137-144
ISBN (Print)978-159593383-6, 1595933832
DOIs
PublikationsstatusErschienen - 01.01.2006
Extern publiziertJa
VeranstaltungInternational Conference on Machine Learning - ICML 2006 - Carnegie Mellon University, Pittsburgh, USA / Vereinigte Staaten
Dauer: 25.06.200629.06.2006
Konferenznummer: 23

DOI

Zuletzt angesehen

Publikationen

  1. The creation and analysis of employer-employee matched data, ed. by John C. Haltiwanger ...
  2. Introduction to the Special Issue Section
  3. Using measures of reading time regularity (RTR) to quantify eye movement dynamics, and how they are shaped by linguistic information
  4. Crop rotation modelling
  5. Embedding Evidence on Conservation Interventions Within a Context of Multilevel Governance
  6. Differentiating forest types using TerraSAR–X spotlight images based on inferential statistics and multivariate analysis
  7. Development of a cell culture system for studying effects of native and photochemically transformed gaseous compounds using an air/liquid culture technique
  8. RAWSim-O: A Simulation Framework for Robotic Mobile Fulfillment Systems
  9. Class size, student performance and Tiebout bias
  10. Experimentally validated multi-step simulation strategy to predict the fatigue crack propagation rate in residual stress fields after laser shock peening
  11. Planar Multipole Resonance Probe: A kinetic model based on a functional analytic description
  12. Ablation Study of a Multimodal Gat Network on Perfect Synthetic and Real-world Data to Investigate the Influence of Language Models in Invoice Recognition
  13. Timing matters: Distinct effects of nitrogen and phosphorus fertilizer application timing on root system architecture responses
  14. Conditions of One-Way and Two-Way Approaches in Strategic Start-Up Communication
  15. Dynamic performance
  16. Perfectly nested or significantly nested - an important difference for conservation management
  17. Proof of concept
  18. Downsizing, Ideology and Contracts
  19. Optimal scheduling of AGVs in a reentrant blocking job-shop
  20. Rethinking Economic Practices and Values As Assemblages of More-Than-Human Relations
  21. Emergence of Responsiveness Across Organizations, Networks, and Clusters from a Dynamic Capability Perspective
  22. Learning with summaries
  23. Facing Up to Third Party Liability for Space Activities
  24. Digital Workplace Transformation Triggers a Shift in the HR Identity
  25. BUSINESS MODELS IN BANKING: A CLUSTER ANALYSIS USING ARCHIVAL DATA
  26. Perception of Space and Time in a Created Environment
  27. Requests for mathematical reasoning in textbooks for primary-level students
  28. Dealing with inclusion–teachers’ assessment of internal and external resources