This is my research repository with links to publications and source code. Please feel free to contact me (details at the bottom) if you are interested in discussing any of the works or arranging a potential collaboration.

2021
  1. Towards a Unified Analysis of Random Fourier Features Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic Journal of Machine Learning Research, Volume 22 (Issue 108), pages 1-51 [abstract] [pdf]
2020
  1. A Deep 2D Convolutional Network for Waveform-based Speech Recognition Dino Oglic, Zoran Cvetkovic, Peter Bell, Steve Renals In Proceedings of the 21st Annual Conference of International Speech Communication Association (INTERSPEECH) [abstract] [pdf] [code]
  2. Deep Scattering Power Spectrum Features for Robust Speech Recognition Neethu M. Joy, Dino Oglic, Zoran Cvetkovic, Peter Bell, Steve Renals In Proceedings of the 21st Annual Conference of International Speech Communication Association (INTERSPEECH) [abstract] [pdf]
2019
  1. Scalable Learning in Reproducing Kernel Krein Spaces Dino Oglic, Thomas Gärtner In Proceedings of the 36th International Conference on Machine Learning (ICML) [abstract] [pdf] [code]
  2. Towards a Unified Analysis of Random Fourier Features Zhu Li, Jean-Francois Ton, Dino Oglic, Dino Sejdinovic In Proceedings of the 36th International Conference on Machine Learning (ICML) Best Paper Award – Honourable Mention
    [abstract] [pdf]
  3. Bayesian Parznets for Robust Speech Recognition in the Waveform Domain Dino Oglic, Zoran Cvetkovic, Peter Sollich Technical report, arXiv:1906.09526 [abstract] [pdf] [code]
2018
  1. Active Search for Computer-Aided Drug Design Dino Oglic, Steven A. Oatley, Simon J. F. Macdonald, Thomas Mcinally, Roman Garnett, Jonathan D. Hirst, Thomas Gärtner Molecular Informatics [abstract] [pdf] [code]
  2. Learning in Reproducing Kernel Kreı̆n Spaces Dino Oglic, Thomas Gärtner In Proceedings of the 35th International Conference on Machine Learning (ICML) [abstract] [pdf] [code]
  3. Constructive Approximation and Learning by Greedy Algorithms Dino Oglic Dissertation, Universitäts-und Landesbibliothek Bonn [abstract] [pdf]
2017
  1. Active Search in Intensionally Specified Structured Spaces Dino Oglic, Roman Garnett, Thomas Gärtner In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence [abstract] [pdf] [code]
  2. Nyström Method with Kernel K-means++ Samples as Landmarks Dino Oglic, Thomas Gärtner In Proceedings of the 34th International Conference on Machine Learning (ICML) [abstract] [pdf] [code]
2016
  1. Greedy Feature Construction Dino Oglic, Thomas Gärtner In Advances in Neural Information Processing Systems 29 (NIPS) [abstract] [pdf] [code]
2014
  1. Learning to Construct Novel Structures Dino Oglic, Roman Garnett, Thomas Gärtner In NIPS Workshop on Discrete and Combinatorial Problems in Machine Learning (DISCML) [abstract] [pdf]
  2. Interactive Knowledge-Based Kernel PCA Dino Oglic, Daniel Paurat, Thomas Gärtner In Machine Learning and Knowledge Discovery in Databases (ECML-PKDD) [abstract] [pdf]
2013
  1. Supervised PCA for Interactive Data Analysis Daniel Paurat, Dino Oglic, Thomas Gärtner In Proceedings of the 2nd NIPS Workshop on Spectral Learning [abstract] [pdf]