dc.contributor.author | Carney, Michael | |
dc.contributor.author | Cunningham, Padraig | |
dc.date.accessioned | 2008-01-29T11:00:44Z | |
dc.date.available | 2008-01-29T11:00:44Z | |
dc.date.issued | 2006-02-10 | |
dc.identifier.citation | Carney, Michael; Cunningham, Padraig. 'Calibrating Probability Density Forecasts with Multi-objective Search'. - Dublin, Trinity College Dublin, Department of Computer Science, TCD-CS-2006-07, 2006, pp12 | en |
dc.identifier.other | TCD-CS-2006-07 | |
dc.description.abstract | In this paper, we show that the optimization of density forecasting models for regression in machine learning can be formulated as a
multi-objective problem.We describe the two objectives of sharpness and
calibration and suggest suitable scoring
metrics for both.We use the popular negative log-likelihood as a measure of sharpness and the probability
integral transform as a measure of calibration. We show how optimization on negative log-likelihood alone often results in sub-optimal models.
To solve this problem we introduce a multi-objective evolutionary optimization framework that can produce better density forecasts from a
prediction users perspective. Our experiments show improvements over
state-of-the-art approaches. | en |
dc.format.extent | 297452 bytes | |
dc.format.mimetype | application/pdf | |
dc.language.iso | en | en |
dc.publisher | Trinity College Dublin, Department of Computer Science | en |
dc.relation.ispartofseries | Computer Science Technical Report | en |
dc.relation.ispartofseries | TCD-CS-2006-07 | en |
dc.relation.haspart | TCD-CS-[no.] | en |
dc.subject | Computer Science | en |
dc.title | Calibrating Probability Density Forecasts with Multi-objective Search | en |
dc.type | Technical Report | en |
dc.identifier.rssuri | https://www.cs.tcd.ie/publications/tech-reports/reports.06/TCD-CS-2006-07.pdf | |
dc.identifier.uri | http://hdl.handle.net/2262/13504 | |