Ata Kaban

Publications

  1. 2020
  2. Accepted/In press

    Optimistic Bounds for Multi-output Prediction

    Henry Reeve & Ata Kaban, 1 Jun 2020, (Accepted/In press) 37th International Conference on Machine Learning (ICML 2020). 14 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. Accepted/In press

    Sufficient Ensemble Size for Random Matrix Theory based Handling of Singular Covariance Matrices

    Ata Kaban, 15 Apr 2020, (Accepted/In press) In : Analysis and Applications. 21 p.

    Research output: Contribution to journalArticle

  4. 2019
  5. Published
  6. Published

    Compressive learning of multi-layer perceptrons: an error analysis

    Ata Kaban, 30 Sep 2019, Proceedings of 2019 International Joint Conference on Neural Networks (IJCNN) . IEEE Computer Society Press, 7 p. N-20494

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  7. Published

    Robust randomized optimization with k nearest neighbors

    Henry Reeve & Ata Kaban, 1 Sep 2019, In : Analysis and Applications. 17, 5, p. 819-836 18 p.

    Research output: Contribution to journalArticle

  8. Published

    Classification with unknown class-conditional label noise on non-compact feature spaces

    Henry Reeve & Ata Kaban, 17 Aug 2019, 32nd Annual Conference on Learning Theory (COLT 19). Proceedings of Machine Learning Research, Vol. 99. p. 2624-2651 28 p. (Proceedings of Machine Learning Research; vol. 99).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  9. Published

    Dimension-free error bounds from random projections

    Ata Kaban, 17 Jul 2019, Thirty Third AAAI Conference on Artificial Intelligence (AAAI-19). AAAI Press, p. 4049-4056 8 p. (Proceedings of the AAAI Conference on Artificial Intelligence; vol. 33, no. 1).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  10. Published

    Fast rates for a kNN classifier robust to unknown asymmetric label noise

    Henry Reeve & Ata Kaban, 15 Jun 2019, Proceedings of the Thirty-sixth International Conference on Machine Learning (ICML 2019). Vol. 97. p. 5401-5409 9 p. (The Proceedings of Machine Learning Research ; vol. 97).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  11. Published

    Exploiting geometric structure in mixture proportion estimation with generalised Blanchard-Lee-Scott estimators

    Henry Reeve & Ata Kaban, 2019, 30th International Conference on Algorithmic Learning Theory (ALT'19). Proceedings of Machine Learning Research, p. 682-699 18 p. (Proceedings of Machine Learning Research; vol. 98).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  12. 2018
  13. E-pub ahead of print

    Tighter guarantees for the compressive multi-layer perceptron

    Ata Kaban, 22 Nov 2018, Theory and Practice of Natural Computing: 7th International Conference, TPNC 2018 Dublin, Ireland, December 12–14, 2018 Proceedings. Fagan, D., Martín-Vide, C., O’Neill, M. & A. Vega-Rodríguez, M. (eds.). Springer, p. 388-400 13 p. (Lecture Notes in Computer Science).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  14. Published

    Joint blind source separation and declipping: a geometric approach for time disjoint sources

    Ata Kaban, 18 Jun 2018, 2017 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) (2017). Institute of Electrical and Electronics Engineers (IEEE), p. 220-225 6 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  15. 2017
  16. Accepted/In press

    On Compressive Ensemble Induced Regularisation: How Close is the Finite Ensemble Precision Matrix to the Infinite Ensemble?

    Ata Kaban, 24 Jul 2017, (Accepted/In press) Proceedings of 28th International Conference on Algorithmic Learning Theory (ALT 2017). JMLR , 15 p. (Proceedings of Machine Learning Research; vol. 76).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  17. 2016
  18. E-pub ahead of print

    How effective is Cauchy-EDA in high dimensions?

    Bob Durrant & Ata Kaban, 21 Nov 2016, Proceedings of the IEEE Congress on Evolutionary Computation 2016. Institute of Electrical and Electronics Engineers (IEEE), 8 p. 16557

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  19. E-pub ahead of print

    Large scale continuous EDA using mutual information

    Ata Kaban, 21 Nov 2016, Proceedings of the IEEE Congress on Evolutionary Computation. Institute of Electrical and Electronics Engineers (IEEE), 8 p. 16598

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  20. E-pub ahead of print

    Finding small sets of random fourier features for shift-invariant kernel approximation

    Frank-Michael Schleif, Ata Kaban & Peter Tino, 9 Sep 2016, Artificial Neural Networks in Pattern Recognition - 7th IAPR TC3 Workshop, ANNPR 2016, Proceedings. Springer Verlag, Vol. 9896 LNAI. p. 42-54 13 p. (Lecture Notes in Computer Science; vol. 9896 LNAI).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  21. Published

    Toward Large-Scale Continuous EDA: A Random Matrix Theory Perspective

    Ata Kaban & Bob Durrant, 13 Jun 2016, In : Evolutionary Computation. 24, 2, p. 255-291 37 p.

    Research output: Contribution to journalArticle

  22. Published

    A New Look at Nearest Neighbours: Identifying Benign Input Geometries via Random Projections

    Ata Kaban, 25 Feb 2016, ACML 2015 Proceedings. JMLR , Vol. 45. p. 65-80 16 p. (Proceedings of Machine Learning Research; vol. 45).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  23. Published

    Non-asymptotic analysis of compressive Fisher discriminants in terms of the effective dimension

    Ata Kaban, 25 Feb 2016, p. 17-32. 16 p.

    Research output: Contribution to conference (unpublished)Paper

  24. Published

    REMEDA: Random Embedding EDA for optimising functions with intrinsic dimension

    Ata Kaban, 2016, Parallel Problem Solving from Nature – PPSN XIV: 14th International Conference, Edinburgh, UK, September 17-21, 2016, Proceedings. Springer, p. 859-868 10 p. (Lecture Notes in Computer Science; vol. 9921).

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  25. 2015
  26. Published

    Improved bounds on the dot product under random projection and random sign projection

    Ata Kaban, 10 Aug 2015, KDD '15 Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: Association for Computing Machinery (ACM), p. 487-496 10 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

Previous 1 2 3 4 5 Next