Zmiana języka

Projects search

Online learning algorithms for complex prediction problems

2016/22/E/ST6/00299

Keywords

Descriptors

  • ST6_11: Uczenie maszynowe, statystyczne przetwarzanie danych i zastosowanie w przetwarzaniu sygnałów
  • ST6_4: Metody formalne, teoretyczne podstawy informatyki w tym informatyka teoretyczna

Panel

ST6 – Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution

Politechnika Poznańska, Wydział Informatyki i Telekomunikacji

Voivodeship: wielkopolskie

Other projects carried out by the institution »

Principal investigator (from the host institution)

dr Wojciech Kotłowski

Number of co-investigators in the project: 3

Call

SONATA BIS 6 – announced on 2016-06-15

Amount awarded
804 700 PLN
Project start date
2017-04-13
Project end date
2023-01-12
Project duration
69 months (the same as in the proposal)
Project status
Project settled

Project description

Download the project description in a pdf file

Note — project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Information in the final report

Publication in academic press/journals (4)

  1. Scale-invariant unconstrained online learning

    Authors:
    Wojciech Kotłowski
    Academic press:
    Theoretical Computer Science (year: 2020, volume: 808, pages: 139-158), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.tcs.2019.11.016 – link to the publication

  2. What makes multi-class imbalanced problems difficult? An experimental study

    Authors:
    Mateusz Lango, Jerzy Stefanowski
    Academic press:
    Expert Systems With Applications (year: 2022, volume: 199, pages: 116962), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.eswa.2022.116962 – link to the publication

  3. On minimaxity of follow the leader strategy in the stochastic setting

    Authors:
    Wojciech Kotłowski
    Academic press:
    Theoretical Computer Science (year: 2018, volume: 742, pages: 50-65), Publisher: Elsevier
    Status:
    Published
    DOI:
    10.1016/j.tcs.2017.12.030 – link to the publication

  4. ViZDoom Competitions: Playing Doom from Pixels

    Authors:
    Marek Wydmuch, Michał Kempka, Wojciech Jaśkowski
    Academic press:
    IEEE Transactions on Games (poprzednio: IEEE Transactions on Computational Intelligence and AI in Games) (year: 2019, volume: 11, pages: 248-259), Publisher: IEEE
    Status:
    Published
    DOI:
    10.1109/TG.2018.2877047 – link to the publication

Articles in post-conference publications (13)

  1. Random Permutation Online Isotonic Regression

    Authors:
    Kotłowski, W., Koolen, W., Malek, A.
    Conference:
    Advances in Neural Information Processing Systems 30 (NIPS 2017) (year: 2017, pages: 4180-4189), Publisher: Curran Associates, Inc.Curr
    Date:
    conference 4-9.12.2017
    Status:
    Published
    DOI:
    link to the publication

  2. The Many Faces of Exponential Weights in Online Learning

    Authors:
    Dirk van der Hoeven, Tim van Erven, Wojciech Kotłowski
    Conference:
    The 31st Annual Conference on Learning Theory (COLT 2018) (year: 2018, pages: http://www.learningtheory.org/colt2018/index.html), Publisher: PMLR
    Date:
    conference 5-9.07.2018
    Status:
    Published
    DOI:
    link to the publication

  3. Scale-Invariant Unconstrained Online Learning

    Authors:
    Wojciech Kotłowski
    Conference:
    The 28th International Conference on Algorithmic Learning Theory (ALT 2017) (year: 2017, pages: 412-433), Publisher: PMLR
    Date:
    conference 15-17.10.2017
    Status:
    Published
    DOI:
    link to the publication

  4. Time aspect in making an actionable prediction of a conversation breakdown

    Authors:
    Janiszewski P., Lango M., Stefanowski J.
    Conference:
    The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD, 2021) (year: 2021, pages: 351–364), Publisher: Springer-Verlag
    Date:
    conference 13-17.09.2021
    Status:
    Published

  5. Open Problem: Fast and Optimal Online Portfolio Selection

    Authors:
    Tim van Erven, Dirk van der Hoeven, Wojciech Kotłowski, Wouter M. Koolen
    Conference:
    The 33rd Annual Conference on Learning Theory (COLT 2020) (year: 2020, pages: 3864-3869), Publisher: PMLR
    Date:
    conference 9-12.07.2020
    Status:
    Published

  6. Learning to crawl

    Authors:
    Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotłowski, David Pal, Balazs Szorenyi
    Conference:
    Thirty-Fourth AAAI Conference on Artificial Intelligence AAAI 2020 (year: 2020, pages: 6046-6053), Publisher: AAAI Press
    Date:
    conference 7-12.02.2020
    Status:
    Published

  7. Adversarial oversampling for multi-class imbalanced data classification with convolutional neural networks

    Authors:
    Adam Wojciechowski, Mateusz Lango
    Conference:
    4th International Workshop on Learning with Imbalanced Domains co-located with ECML/PKDD (year: 2022, pages: 98-111), Publisher: JMLR.org
    Date:
    conference 19-23.09.2022
    Status:
    Published
    DOI:
    link to the publication

  8. Robust Online Convex Optimization in the Presence of Outliers

    Authors:
    Tim van Erven, Sarah Sachs, Wouter M. Koolen, Wojciech Kotlowski
    Conference:
    The 34th Annual Conference on Learning Theory (COLT 2021) (year: 2021, pages: 4174-4194), Publisher: PMLR
    Date:
    conference 15-19.08.2021
    Status:
    Published
    DOI:
    link to the publication

  9. Bandit Principal Component Analysis

    Authors:
    Wojciech Kotłowski, Gergely Neu
    Conference:
    Thirty-Second Conference on Learning Theory (COLT) (year: 2019, pages: 1994-2024), Publisher: JMLR.org
    Date:
    conference 43641
    Status:
    Published
    DOI:
    link to the publication

  10. Prototypical Convolutional Neural Network for a phrase-based explanation of sentiment classification

    Authors:
    Kamil Pluciński, Mateusz Lango, Jerzy Stefanowski
    Conference:
    ECML PKDD International Workshop and Tutorial on eXplainable Knowledge Discovery in Data Mining (XKDD) (year: 2021, pages: 457-472), Publisher: Springer-Verlag
    Date:
    conference 13-17.09.2021
    Status:
    Published

  11. A case where a spindly two-layer linear network decisively outperforms any neural network with a fully connected input layer

    Authors:
    Manfred K. Warmuth, Wojciech Kotlowski, Ehsan Amid
    Conference:
    The 32nd International Conference on Algorithmic Learning Theory (ALT 2021) (year: 2021, pages: 1214-1236), Publisher: PMLR
    Date:
    conference 16-19.03.2021
    Status:
    Published
    DOI:
    link to the publication

  12. Adaptive scale-invariant online algorithms for learning linear models

    Authors:
    Michał Kempka, Wojciech Kotłowski, Manfred K. Warmuth
    Conference:
    36th International Conference on Machine Learning (ICML) (year: 2019, pages: 3321-3330), Publisher: JMLR.org
    Date:
    conference 43625
    Status:
    Published
    DOI:
    link to the publication

  13. Online Principal Component Analysis for Evolving Data Streams

    Authors:
    Monika Grabowska, Wojciech Kotłowski
    Conference:
    International Symposium on Computer and Information Sciences (ISCIS 2018) (year: 2018, pages: https://projekty.iitis.pl/iscis2018), Publisher: Springer
    Date:
    conference 20-21.09.2018
    Status:
    Published

« New search

Graphic design and implementation: Jakub Piotrowski