Research Scientist
Mathematics Cluster
Frame Theory and its Implementation
Machine Learning

Tel. +43 1 51581-2545
Email: daniel.haider(at)oeaw.ac.at

 

Academic Background

Daniel Haider studied mathematics at the University of Vienna, with an emphasis on applied mathematics and scientific computing. In 2019, he wrote his master’s thesis titled "Aspects of Time-Frequency Scattering and Towards Phase Scattering." In 2025, he defended his dissertation “Invertibility and Stability in Neural Networks: Tools from Frame Theory” with distinction. Both theses were supervised by Peter Balazs. Since 2025, he has been a postdoctoral researcher at ARI on the ELECOM project.

Current Research

Daniel’s research is twofold. On the one hand, he approaches machine learning concepts using tools from abstract mathematics. His work focuses on numerical stability and invertibility of ReLU layers, the design of stable convolutional architectures for various applications, and the derivation of statistical properties of randomly initialized neural networks. On the other hand, he develops machine learning solutions for bioacoustics, including automatic activity detection, localization, classification, annotation tools, and sound synthesis. His current focus is on the analysis and synthesis of rumbles produced by African savanna elephants.

 

Publications

  • Optimal lower Lipschitz bounds for ReLU layers, saturation, and phase retrieval. / Freeman, Daniel; Haider, Daniel.
    In: Applied and Computational Harmonic Analysis, Vol. 79, 101801, 15.01.2026.
    DOIWebsiteRISENWBIB
  • Injectivity of ReLU Layers: Tools from Frame Theory. / Haider, Daniel; Ehler, Martin; Balazs, Peter.
    In: Mathematical Foundations of Machine Learning, Vol. 1, No. 1, 08.10.2025.
    DOIRISENWBIB
  • ISAC: An Invertible and Stable Auditory Filter Bank with Customizable Kernels for ML Integration. / Haider, Daniel; Perfler, Felix; Balazs, Peter et al.
    2025 International Conference on Sampling Theory and Applications (SampTA). IEEE, 2025.
    DOIRISENWBIB
  • Residual Hybrid Filterbanks. / Lostanlen, Vincent; Zhang, Xiran ; Haider, Daniel et al.
    2025 IEEE Statistical Signal Processing Workshop (SSP). IEEE, 2025.
    DOIRISENWBIB
  • Invertibility of ReLU-Layers: A Practical Approach. / Eckert, H; Haider, D; Ehler, M et al.
    Proceedings of the 16th International Joint Conference on Computational Intelligence - NCTA. Porto: SciTePress, 2024. p. 423-429.
    DOIRISENWBIB
  • How to Draw Audio: An Intuitive Introduction to Spectograms. / Haider, D; Köhldorfer, L.
    In: N/A, Vol. 2, No. 2, 15.11.2024, p. 6-8.
    WebsiteDownloadRISENWBIB
  • Hold Me Tight: Stable Encoder-Decoder Design for Speech Enhancement. / Haider, D; Perfler, F; Lostanlen, V et al.
    Proceedings of the Interspeech 2024. Kos, 2024. p. 5013-5017.
    DOIRISENWBIB
  • Trainable signal encoders that are robust against noise. / Balazs, P; Haider, D; Lostanlen, V et al.
    Proceedings of the Internoise 2024. Nantes, F, 2024.
    RISENWBIB
  • (Almost) Smooth Sailing: Towards Numerical Stability of Neural Networks Through Differentiable Regularization of the Condition Number. / Nenov, R; Haider, D; Balazs, P.
    ICML 2024 Workshop on Differentiable Almost Everything: Differentiable Relaxations, Algorithms, Operators, and Simulators. Vienna, 2024.
    RISENWBIB
  • Instabilities in Convnets for Raw Audio. / Haider, D; Lostanlen, V; Ehler, M et al.
    In: IEEE Signal Processing Letters, Vol. 31, 08.04.2024, p. 1084-1088.
    DOIRISENWBIB
  • Fitting Auditory Filterbanks with Multiresolution Neural Networks. / Lostanlen, V; Haider, D; Han, H et al.
    2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. New Paltz, USA: IEEE, 2023.
    RISENWBIB
  • Convex Geometry of ReLU-Layers, Injectivity on the Ball and Local Reconstruction. / Haider, D; Ehler, M; Balazs, P.
    Proceedings of the 40th International Conference on Machine Learning. Honolulu, 2023.
    RISENWBIB
  • Double Preconditioning for Gabor Frame Operators: Algebraic, Functional Analytic and Numerical Aspects. / Feichtinger, H; Balazs, P; Haider, D.
    In: Applied and Computational Harmonic Analysis, Vol. 66, 10.05.2023, p. 101-137.
    DOIRISENWBIB
  • Phase-based Signal Representations for Scattering. / Haider, D; Balazs, P; Holighaus, N.
    Proceedings of the 29th European Signal Processing Conference. Dublin, 2021.
    RISENWBIB
  • Extraction of Rhythmical Features with the Gabor Scattering Transform. / Haider, D; Balazs, P.
    Proceedings of the 14th International Symposium on Computer Music Multidisciplinary Research (CMMR), Marseille, France, Oct. 14-18. 2019. p. 916-923.
    RISENWBIB
  • Aspects of Time-Frequency Scattering and Introducing Phase Scattering. / Haider, Daniel.
    Universität Wien, 2019.
    RISENWBIB
  • 1