Publications

Preprints

[2]

Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery

J. Sauder, M. Genzel, P. JungarXiv:2202.03391, 2022.AbstractBibTeX ● Links:
[1]

The Separation Capacity of Random Neural Networks

S. Dirksen, M. Genzel, L. Jacques, A. StollenwerkarXiv:2108.00207, 2021.AbstractBibTeX ● Links:

Journal Articles

[13]

Generic Error Bounds for the Generalized Lasso with Sub-Exponential Data

M. Genzel, Ch. Kipp Sampling Theory, Signal Processing, and Data Analysis, online, 20 (15), 2022.AbstractBibTeX ● Links:
[12]

A Unified Approach to Uniform Signal Recovery From Nonlinear Observations

M. Genzel, A. StollenwerkFound. Comut. Math., online, 2022.AbstractBibTeX ● Links:
[11]

Compressed Sensing with 1D Total Variation: Breaking Sample Complexity Barriers via Non-Uniform Recovery

M. Genzel, M. März, R. SeidelInf. Inference, 11 (1), pp. 203-250, 2022.AbstractBibTeX ● Links:
[10]

Solving Inverse Problems With Deep Neural Networks - Robustness Included?

M. Genzel, J. Macdonald, M. MärzIEEE Trans. Pattern Anal. Mach. Intell., online, 2022.AbstractBibTeX ● Links:
[9]

L1-Analysis Minimization and Generalized (Co-)Sparsity: When Does Recovery Succeed?

M. Genzel, G. Kutyniok, M. MärzAppl. Comput. Harmon. Anal., 52 , pp. 82–140, 2021.AbstractBibTeX ● Links:
[8]

EDDIDAT: a graphical user interface for the analysis of energy-dispersive diffraction data

D. Apel, M. Genzel, M. Meixner, M. Boin, M. Klaus, Ch. GenzelJ. Appl. Cryst., 53 (4), pp. 1130–1137, 2020.AbstractBibTeX ● Links:
[7]

Robust 1-Bit Compressed Sensing via Hinge Loss Minimization

M. Genzel, A. StollenwerkInf. Inference, 9 (2), pp. 361–422, 2020.AbstractBibTeX ● Links:
[6]

Recovering Structured Data From Superimposed Non-Linear Measurements

M. Genzel, P. JungIEEE Trans. Inf. Theory, 66 (1), pp. 453–477, 2020.AbstractBibTeX ● Links:
[5]

High-Dimensional Estimation of Structured Signals From Non-Linear Observations With General Convex Loss Functions

M. GenzelIEEE Trans. Inf. Theory, 63 (3), pp. 1601–1619, 2017.AbstractBibTeX ● Links:
[4]

Sparse Proteomics Analysis - a compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data

T. Conrad, M. Genzel, N. Cvetkovic, N. Wulkow, A. Leichtle, J. Vybiral, G. Kutyniok, Ch. SchütteBMC Bioinform., 18 , pp. 160, 2017.AbstractBibTeX ● Links:
[3]

Diffraction analysis of strongly inhomogeneous residual stress depth distributions by modification of the stress scanning method. II. Experimental implementation

M. Meixner, T. Fuss, M. Klaus, M. Genzel, Ch. GenzelJ. Appl. Cryst., 48 (5), pp. 1451–1461, 2015.AbstractBibTeX ● Links:
[2]

Asymptotic Analysis of Inpainting via Universal Shearlet Systems

M. Genzel, G. KutyniokSIAM J. Imaging Sci., 7 (4), pp. 2301–2339, 2014.AbstractBibTeX ● Links:
[1]

Rietveld-based energy-dispersive residual stress evaluation: Analysis of complex stress fields σij(z)

D. Apel, M. Klaus, M. Genzel, Ch. GenzelJ. Appl. Cryst., 47 (2), pp. 511–526, 2014.AbstractBibTeX ● Links:

Technical Reports

[3]

AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry

M. Genzel, J. Macdonald, M. MärzarXiv:2106.00280, 2021.AbstractBibTeX ● Links:
[2]

The Mismatch Principle: The Generalized Lasso Under Large Model Uncertainties

M. Genzel, G. KutyniokarXiv:1808.06329, 2018.AbstractBibTeX ● Links:
[1]

A Mathematical Framework for Feature Selection from Real-World Data with Non-Linear Observations

M. Genzel, G. KutyniokarXiv:1608.08852, 2016.AbstractBibTeX ● Links:

Conference & Workshop Articles

[9]

Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

M. Genzel, I. Gühring, J. Macdonald, M. März ICML 2022 (long talk: 118/5630 = 2%), 2022.AbstractBibTeX ● Links:
[8]

Near-Exact Recovery for Sparse-View CT via Data-Driven Methods

M. Genzel, I. Gühring, J. Macdonald, M. März NeurIPS 2021 Workshop on Deep Learning and Inverse Problems, 2021.AbstractBibTeX ● Links:
[7]

Learning Structured Sparse Matrices for Signal Recovery via Unrolled Optimization

J. Sauder, M. Genzel, P. JungNeurIPS 2021 Workshop on Deep Learning and Inverse Problems, 2021.AbstractBibTeX ● Links:
[6]

Compressed Sensing with 1D Total Variation: Breaking Sample Complexity Barriers via Non-Uniform Recovery (iTWIST'20)

M. Genzel, M. März, R. SeidelProceedings of the International Traveling Workshop on Interactions Between Low-Complexity Data Models and Sensing Techniques (iTWIST), arXiv.org, 2020.AbstractBibTeX ● Links:
[5]

Robust 1-Bit Compressed Sensing via Hinge Loss Minimization

M. Genzel, A. StollenwerkProceedings of the 13th International Conference on Sampling Theory and Applications (SampTA), IEEE, 2019.AbstractBibTeX ● Links:
[4]

A New Perspective on the Sample Complexity of the Analysis Basis Pursuit

M. Genzel, G. Kutyniok, M. März5th International Workshop on Compressed Sensing applied to Radar, Multimodal Sensing, and Imaging (CoSeRa), EURASIP, 2018.AbstractBibTeX ● Links:
[3]

Blind Sparse Recovery Using Imperfect Sensor Networks

P. Jung, M. GenzelProceedings of the 2018 IEEE Statistical Signal Processing Workshop (SSP), pp. 598–602, IEEE, 2018.AbstractBibTeX ● Links:
[2]

Blind sparse recovery from superimposed non-linear sensor measurements

M. Genzel, P. JungProceedings of the 12th International Conference on Sampling Theory and Applications (SampTA), pp. 106–110, IEEE, 2017.AbstractBibTeX ● Links:
[1]

Keynote Lecture: Residual Stress Gradient Analysis by Multiple Diffraction Line Methods

Ch. Genzel, D. Apel, M. Klaus, M. Genzel, D. Balzar ● Kurz, S J B, Mittemeijer, E J, Scholtes, B (Ed.): International Conference on Residual Stresses 9 (ICRS 9), pp. 3–18, Trans Tech Publications Ltd., 2013.AbstractBibTeX ● Links:

Other Publications

[2]

Artificial Neural Networks

M. Genzel, G. KutyniokGAMM Rundbrief, 2019 (2), pp. 12–18, 2019.BibTeX ● Links:
[1]

The Mismatch Principle: An Ignorant Approach to Non-Linear Compressed Sensing? (joint with G. Kutyniok and P. Jung)

M. GenzelOberwolfach Report, 15 (1), pp. 781–782, 2018.BibTeX ● Links:

Monographs

[3]

The Mismatch Principle and L1-Analysis Compressed Sensing: A Unified Approach to Estimation Under Large Model Uncertainties and Structural Constraints

M. GenzelPh.D. Thesis, Technische Universität Berlin, 2019.BibTeX ● Links:
[2]

Sparse Proteomics Analysis: Toward a Mathematical Foundation of Feature Selection and Disease Classification

M. GenzelMaster's Thesis, Technische Universität Berlin, 2015.BibTeX
[1]

Analysis von Inpainting mittels Hybrid-Shearlets und Clustered Sparsity

M. GenzelBachelor's Thesis, Technische Universität Berlin, 2013, (in german).BibTeX