Publications

Preprints

  • Convergence of alternating minimisation algorithms for dictionary learning
    S. Ruetz and K. Schnass
    arXiv:2304.01768, 2023. [pdf]

  • Non-asymptotic bounds for inclusion probabilities in rejective sampling
    S. Ruetz and K. Schnass
    arXiv:2212.09391, 2022. [pdf]

Journal

  • Dictionary learning - from local towards global and adaptive
    M.C. Pali and K. Schnass
    Information and Inference: A Journal of the IMA, 12(3):1295–1346, 2023. [v1pdf] [v2pdf] [toolbox]

  • Average performance of OMP and Thresholding under dictionary mismatch
    M.C. Pali, S. Ruetz and K. Schnass
    IEEE Signal Processing Letters, 29:1077–1081, 2022. [pdf]

  • Submatrices with non-uniformly selected random supports and insights into sparse approximation
    S. Ruetz and K. Schnass
    SIAM Journal on Matrix Analysis and Applications (SIMAX), 42(3):1268–1289, 2021. [pdf]

  • Compressed dictionary learning
    K. Schnass and F. Teixeira
    Journal of Fourier Analysis and Applications 26, Art. Nr. 33, 2020. [pdf] [probox] [toybox]

  • Online and stable learning of analysis operators
    M. Sandbichler and K. Schnass
    IEEE Transactions on Signal Processing, 67(1):41–53, 2019. [pdf] [toolbox]

  • Average performance of Orthogonal Matching Pursuit (OMP) for sparse approximation
    K. Schnass
    IEEE Signal Processing Letters (arXiv:1809.06684), 25(12):1865–1869, 2018. [pdf]

  • Fast dictionary learning from incomplete data
    V. Naumova and K. Schnass
    EURASIP Journal on Advances in Signal Processing, 2018. [pdf] [toolbox]

  • Convergence radius and sample complexity of ITKM algorithms for dictionary learning
    K. Schnass
    Applied and Computational Harmonic Analysis, 45(1):22–58, 2018. [pdf] [toolbox]

  • Local Identification of Overcomplete Dictionaries
    K. Schnass
    Journal of Machine Learning Research (arXiv:1401.6354), 16(Jun):1211--1242, 2015. [pdf] [toolbox]

  • On the Identifiability of Overcomplete Dictionaries via the Minimisation Principle Underlying K-SVD
    K. Schnass
    Applied and Computational Harmonic Analysis, 37(3):464--491, 2014. [pdf]

  • Learning functions of few arbitrary linear parameters in high dimensions
    M. Fornasier, K. Schnass and J. Vybiral
    Foundations of Computational Mathematics, 12(2):229--262, 2012. [pdf]

  • Classification via incoherent subspaces
    K. Schnass and P. Vandergheynst
    Rejecta Mathematica, 2(1):1--18, 2011. [pdf]

  • Dictionary identification - sparse matrix-factorisation via l1-minimisation
    R. Gribonval and K. Schnass
    IEEE Transactions on Information Theory, 56(7):3523--3539, 2010. [pdf]

  • Atoms of all channels, unite! Average case analysis of multi-channel sparse recovery using greedy algorithms
    R. Gribonval, H. Rauhut, K. Schnass and P. Vandergheynst
    Journal of Fourier Analysis and Applications, 14(5):655--687, 2008. [pdf]

  • Compressed sensing and redundant dictionaries
    H. Rauhut, K. Schnass and P. Vandergheynst
    IEEE Transactions on Information Theory, 54(5):2210--2219, 2008. [pdf]

  • Dictionary preconditioning for greedy algorithms
    K. Schnass and P. Vandergheynst
    IEEE Transactions on Signal Processing, 56(5):1994--2002, 2008. [pdf]

  • Average performance analysis for thresholding
    K. Schnass and P. Vandergheynst
    IEEE Signal Processing Letters, 14(11):828--831, 2007. [pdf]

Conference

  • A good reason for using OMP: average case results
    K. Schnass
    SPARS19. [extended abstract]

  • The adaptive dictionary learning toolbox
    C. Rusu and K. Schnass
    SPARS19. [extended abstract]

  • Relaxed contractivity conditions for dictionary learning via Iterative Thresholding and K residual Means
    M.C. Pali, K. Schnass and A. Steinicke
    SPARS19. [extended abstract]

  • Sequential learning of analysis operators
    M. Sandbichler and K. Schnass
    SPARS17. [extended abstract]

  • Compressed dictionary learning
    F. Teixeira and K. Schnass
    SPARS17. [extended abstract]

  • Dictionary learning from incomplete data for efficient image restoration
    V. Naumova and K. Schnass
    EUSIPCO17. [pdf] [toolbox]

  • Dictionary identification results for K-SVD with sparsity parameter 1
    K. Schnass
    SampTA13. [pdf]

  • Learning functions of few arbitrary linear parameters in high dimensions
    M. Fornasier, K. Schnass, and J. Vybiral
    SampTA11. [pdf]

  • Compressed learning of high-dimensional sparse functions
    K. Schnass and J. Vybiral
    ICASSP11. [pdf]

  • A union of incoherent spaces model for classification
    K. Schnass and P. Vandergheynst
    ICASSP10. [pdf]

  • Basis identification from random sparse samples
    R. Gribonval and K. Schnass
    SPARS09. [pdf]

  • Dictionary identifiability from few training samples
    R. Gribonval and K. Schnass
    EUSIPCO08. [pdf]

  • Some recovery conditions for basis learning by l_1-minimization
    R. Gribonval and K. Schnass
    ISCCSP08. [pdf]

  • Dictionary learning based dimensionality reduction for classification
    K. Schnass and P. Vandergheynst
    ISCCSP08. [pdf]

  • Multichannel thresholding with sensing dictionaries
    R. Gribonval, B. Mailhe, H. Rauhut, K. Schnass and P. Vandergheynst
    CAMSAP07. [pdf]

  • Average case analysis of multichannel sparse approximations using p- thresholding
    R. Gribonval, B. Mailhe, H. Rauhut, K. Schnass and P. Vandergheynst
    SPIE Optics and Photonics, Wavelets XII, 2007. [pdf]

  • Average case analysis of multichannel thresholding
    R. Gribonval, B. Mailhe, H. Rauhut, K. Schnass and P. Vandergheynst
    ICASSP07. [pdf]

Theses

  • Dictionary Learning & Related Topics
    venia docendi, University of Innsbruck, 2018. [outline]

  • Sparsity & Dictionaries - Algorithms & Design
    PhD Thesis n.4349, Swiss Federal Institute of Technology Lausanne, EPFL, 2009.  [pdf]

  • Gabor Multipliers - A Self-Contained Survey
    Master's Thesis, University of Vienna, Austria, 2004. [pdf]

Other

  • A Personal Introduction to Theoretical Dictionary Learning
    K. Schnass
    Internationale Mathematische Nachrichten (Bulletin of the Austrian Mathematical Society), 228:5--15, 2015. [pdf]

Copyright Blabla

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

 

Nach oben scrollen