Consistent and scalable learning algorithms for structured output prediction
2013/09/D/ST6/03917
Keywords
Descriptors
- ST6_11: Uczenie maszynowe, statystyczne przetwarzanie danych i zastosowanie w przetwarzaniu sygnałów
- ST6_7: Sztuczna inteligencja, systemy inteligentne i wieloagentowe
Panel
ST6 – Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems
Host institution
Politechnika Poznańska, Wydział Informatyki
Voivodeship: wielkopolskie
Principal investigator (from the host institution)
dr Krzysztof Jerzy Dembczyński
Number of co-investigators in the project: 2
Call
SONATA 5 – announced on 2013-03-15
- Amount awarded
- 393 900 PLN
- Project start date
- 2014-03-24
- Project end date
- 2017-03-23
- Project duration
- 36 months (the same as in the proposal)
- Project status
- Project settled
Information in the final report
Publication in academic press/journals (4)
-
Extreme classification under limited space and time budget
- Authors:
- Kalina Jasinska, Krzysztof Dembczyński
- Academic press:
- Schedae Informaticae (year: 2016, volume: 25, pages: 46288), Publisher: Uniwersytet Jagielloński
- Status:
- Published
- DOI:
- 10.4467/20838476SI.16.001.6182 – link to the publication
-
Multi-target prediction: a unifying view on problems and methods
- Authors:
- Willem Waegeman, Krzysztof Dembczyński, Eyke Hüllermeier
- Academic press:
- Data Mining and Knowledge Discovery (year: 2019, volume: 33, pages: 293–324), Publisher: Springer
- Status:
- Published
- DOI:
- 10.1007/s10618-018-0595-5 – link to the publication
-
Surrogate regret bounds for generalized classification performance metrics
- Authors:
- Wojciech Kotlowski, Krzysztof Dembczynski
- Academic press:
- Machine Learning (year: 2017, volume: 106, pages: 549-572), Publisher: Springer
- Status:
- Published
- DOI:
- 10.1007/s10994-016-5591-7 – link to the publication
-
Exact and efficient top-K inference for multi-target prediction by querying separable linear relational models
- Authors:
- Michiel Stock, Krzysztof Dembczyński, Bernard De Baets, Willem Waegeman
- Status:
- Accepted for publication
Articles in post-conference publications (3)
-
Surrogate regret bounds for generalized classification performance metrics
- Authors:
- Wojciech Kotłowski, Krzysztof Dembczyński
- Conference:
- Asian Conference on Machine Learning (year: 2015, pages: 301-316), Publisher: JMLR: Workshop and Conference Proceedings
- Date:
- conference 20-22/11/2015
- Status:
- Published
- DOI:
- link to the publication
-
Online F-Measure Optimization
- Authors:
- Róbert Busa-Fekete, Balázs Szörényi, Krzysztof Dembczyński, Eyke Hüllermeier
- Conference:
- Advances in Neural Information Processing Systems 28 (NIPS 2015) (year: 2015, pages: 595-603), Publisher: Curran Associates, Inc.
- Date:
- conference 7-12/12/2015
- Status:
- Published
- DOI:
- link to the publication
-
Extreme F-measure Maximization using Sparse Probability Estimates
- Authors:
- Kalina Jasinska, Krzysztof Dembczynski, Róbert Busa-Fekete, Karlson Pfannschmidt, Timo Klerx, Eyke Hüllermeier
- Conference:
- International Conference on Machine Learning (year: 2016, pages: 1435-1444), Publisher: Proceedings of Machine Learning Research
- Date:
- conference 20-22 czerwiec 2016
- Status:
- Published
- DOI:
- link to the publication
Book publications / chapters in book publications (1)
-
Consistency of Probabilistic Classifier Trees
- Authors:
- Krzysztof Dembczynski, Wojciech Kotlowski, Willem Waegeman, Róbert Busa-Fekete, Eyke Hüllermeier
- Book:
- ECML PKDD 2016: Machine Learning and Knowledge Discovery in Databases (year: 2016, volume: 9852, pages: 511-526), Publisher: Springer
- Status:
- Published
- DOI:
- link to the publication