Johannes Maly
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Johannes Maly has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Sjoerd Dirksen
Mathematical Institute, Utrecht University, Utrecht, The Netherlands
3 shared publications Alexander Stollenwerk
ISPGroup, ICTEAM Institute, UCLouvain, Louvain-la-Neuve, Belgium
2 shared publicationsHans Christian Jung
DeepL, Cologne, Germany
2 shared publicationsLars Palzer
Signal Iduna group, Hamburg, Germany
2 shared publications- Sara Krause-Solberg
Helmholtz Imaging, Deutsches Elektronen-Synchrotron DESY, Hamburg, Germany
2 shared publications - Valeriya Naumova
Simula Consulting and SimulaMet
2 shared publications
Latest Publications
- Open Access
- 26 August 2026
- Published by Springer Nature in Advances in Computational Mathematics
- Vol. 52 (5) , 75
How to induce regularization in linear models: a guide to reparametrizing gradient flow
In this work, we analyze the relation between reparametrizations of gradient flow and the induced implicit bias in linear models, which encompass various basic regression tasks. In particular, we study how reparametrization, loss function, and link function influence the convergence behavior and implicit bias of gradient flow. Our results provide conditions under which the implicit bias can be well-described and convergence of the flow is guaranteed. We furthermore show how to use these insights for designing reparametrization functions that lead to specific implicit biases which are closely connected to $$\ell _p$$ - or trigonometric regularizers.- 26 August 2026
- Published by Springer Nature in Advances in Computational Mathematics
- Vol. 52 (5) , 75
Open AccessHow to induce regularization in linear models: a guide to reparametrizing gradient flow
In this work, we analyze the relation between reparametrizations of gradient flow and the induced implicit bias in linear models, which encompass various basic regression tasks. In particular, we study how reparametrization, loss function, and link function influence the convergence behavior and implicit bias of gradient flow. Our results provide conditions under which the implicit bias can be well-described and convergence of the flow is guaranteed. We furthermore show how to use these insights for designing reparametrization functions that lead to specific implicit biases which are closely connected to $$\ell _p$$ - or trigonometric regularizers. - 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (10) , 8149-8168
Subspace and DOA Estimation Under Coarse Quantization
We study direction-of-arrival (DOA) estimation from coarsely quantized data. We focus on a two-step approach which first estimates the signal subspace via covariance estimation and then extracts DOA angles by the ESPRIT algorithm. In particular, we analyze two stochastic quantization schemes which use dithering: a one-bit quantizer combined with rectangular dither and a multi-bit quantizer with triangular dither. For each quantizer, we derive rigorous high probability bounds for the distances between the true and estimated signal subspaces and DOA angles. Using our analysis, we identify scenarios in which subspace and DOA estimation via triangular dithering qualitatively outperforms rectangular dithering. We verify in numerical simulations that our estimates are optimal in their dependence on the smallest non-zero eigenvalue of the target matrix. The resulting subspace estimation guarantees are equally applicable in the analysis of other spectral estimation algorithms and related problems.
- 13 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 71 (10) , 8149-8168
Subspace and DOA Estimation Under Coarse Quantization
We study direction-of-arrival (DOA) estimation from coarsely quantized data. We focus on a two-step approach which first estimates the signal subspace via covariance estimation and then extracts DOA angles by the ESPRIT algorithm. In particular, we analyze two stochastic quantization schemes which use dithering: a one-bit quantizer combined with rectangular dither and a multi-bit quantizer with triangular dither. For each quantizer, we derive rigorous high probability bounds for the distances between the true and estimated signal subspaces and DOA angles. Using our analysis, we identify scenarios in which subspace and DOA estimation via triangular dithering qualitatively outperforms rectangular dithering. We verify in numerical simulations that our estimates are optimal in their dependence on the smallest non-zero eigenvalue of the target matrix. The resulting subspace estimation guarantees are equally applicable in the analysis of other spectral estimation algorithms and related problems.
- 26 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 70 (7) , 5228-5247
Tuning-Free One-Bit Covariance Estimation Using Data-Driven Dithering
We consider covariance estimation of any subgaussian distribution from finitely many i.i.d. samples that are quantized to one bit of information per entry. Recent work has shown that a reliable estimator can be constructed if uniformly distributed dithers on [-λ,λ] are used in the one-bit quantizer. This estimator enjoys near-minimax optimal, non-asymptotic error estimates in the operator and Frobenius norms if λ is chosen proportional to the largest variance of the distribution. However, this quantity is not known a-priori, and in practice λ needs to be carefully tuned to achieve good performance. In this work we resolve this problem by introducing a tuning-free variant of this estimator, which replaces λ by a data-driven quantity. We prove that this estimator satisfies the same non-asymptotic error estimates — up to small (logarithmic) losses and a slightly worse probability estimate. We also show that by using refined data-driven dithers that vary per entry of each sample, one can construct an estimator satisfying the same estimation error bound as the sample covariance of the samples before quantization — again up logarithmic losses. Our proofs rely on a new version of the Burkholder-Rosenthal inequalities for matrix martingales, which is expected to be of independent interest.
- 26 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Theory
- Vol. 70 (7) , 5228-5247
Tuning-Free One-Bit Covariance Estimation Using Data-Driven Dithering
We consider covariance estimation of any subgaussian distribution from finitely many i.i.d. samples that are quantized to one bit of information per entry. Recent work has shown that a reliable estimator can be constructed if uniformly distributed dithers on [-λ,λ] are used in the one-bit quantizer. This estimator enjoys near-minimax optimal, non-asymptotic error estimates in the operator and Frobenius norms if λ is chosen proportional to the largest variance of the distribution. However, this quantity is not known a-priori, and in practice λ needs to be carefully tuned to achieve good performance. In this work we resolve this problem by introducing a tuning-free variant of this estimator, which replaces λ by a data-driven quantity. We prove that this estimator satisfies the same non-asymptotic error estimates — up to small (logarithmic) losses and a slightly worse probability estimate. We also show that by using refined data-driven dithers that vary per entry of each sample, one can construct an estimator satisfying the same estimation error bound as the sample covariance of the samples before quantization — again up logarithmic losses. Our proofs rely on a new version of the Burkholder-Rosenthal inequalities for matrix martingales, which is expected to be of independent interest.
- 20 June 2023
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 67, 101569
Robust sensing of low-rank matrices with non-orthogonal sparse decomposition
- 20 June 2023
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 67, 101569
Robust sensing of low-rank matrices with non-orthogonal sparse decomposition
- 2 May 2023
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 66, 138-150
A simple approach for quantizing neural networks
- 2 May 2023
- Published by Elsevier in Applied and Computational Harmonic Analysis
- Vol. 66, 138-150
A simple approach for quantizing neural networks
- 22 October 2022
- Published by Springer Nature
- p. 77-104
New Challenges in Covariance Estimation: Multiple Structures and Coarse Quantization
- 22 October 2022
- Published by Springer Nature
- p. 77-104
New Challenges in Covariance Estimation: Multiple Structures and Coarse Quantization
- 23 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 70 (1053587X) , 280-291
Structural Sparsity in Multiple Measurements
We propose a novel sparsity model for distributed compressed sensing in the multiple measurement vectors (MMV) setting. Our model extends the concept of row-sparsity to allow more general types of structured sparsity arising in a variety of applications like, e.g., seismic exploration and non-destructive testing. To reconstruct structured data from observed measurements, we derive a non-convex but well-conditioned LASSO-type functional. By exploiting the convex-concave geometry of the functional, we design a projected gradient descent algorithm and show its effectiveness in extensive numerical simulations, both on toy and real data.
- 23 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 70 (1053587X) , 280-291
Structural Sparsity in Multiple Measurements
We propose a novel sparsity model for distributed compressed sensing in the multiple measurement vectors (MMV) setting. Our model extends the concept of row-sparsity to allow more general types of structured sparsity arising in a variety of applications like, e.g., seismic exploration and non-destructive testing. To reconstruct structured data from observed measurements, we derive a non-convex but well-conditioned LASSO-type functional. By exploiting the convex-concave geometry of the functional, we design a projected gradient descent algorithm and show its effectiveness in extensive numerical simulations, both on toy and real data.
- Open Access
- 14 December 2021
- Published by Wiley in Proceedings in Applied Mathematics and Mechanics
- Vol. 21 (1) , e202100063
Covariance Estimation under One‐bit Quantization
We consider the classical problem of estimating the covariance matrix of a subgaussian distribution from i.i.d. samples in the novel context of coarse quantization, i.e., instead of having full knowledge of the samples, they are quantized to one or two bits per entry. This problem occurs naturally in signal processing applications. We introduce new estimators in two different quantization scenarios and derive non‐asymptotic estimation error bounds in terms of the operator norm. In the first scenario we consider a simple, scale‐invariant one‐bit quantizer and derive an estimation result for the correlation matrix of a centered Gaussian distribution. In the second scenario, we add random dithering to the quantizer. In this case we can accurately estimate the full covariance matrix of a general subgaussian distribution by collecting two bits per entry of each sample. In both scenarios, our bounds apply to masked covariance estimation as well. We demonstrate the near‐optimality of our error bounds by deriving corresponding (minimax) lower bounds and using numerical simulations.
- 14 December 2021
- Published by Wiley in Proceedings in Applied Mathematics and Mechanics
- Vol. 21 (1) , e202100063
Open AccessCovariance Estimation under One‐bit Quantization
We consider the classical problem of estimating the covariance matrix of a subgaussian distribution from i.i.d. samples in the novel context of coarse quantization, i.e., instead of having full knowledge of the samples, they are quantized to one or two bits per entry. This problem occurs naturally in signal processing applications. We introduce new estimators in two different quantization scenarios and derive non‐asymptotic estimation error bounds in terms of the operator norm. In the first scenario we consider a simple, scale‐invariant one‐bit quantizer and derive an estimation result for the correlation matrix of a centered Gaussian distribution. In the second scenario, we add random dithering to the quantizer. In this case we can accurately estimate the full covariance matrix of a general subgaussian distribution by collecting two bits per entry of each sample. In both scenarios, our bounds apply to masked covariance estimation as well. We demonstrate the near‐optimality of our error bounds by deriving corresponding (minimax) lower bounds and using numerical simulations.
- Open Access
Quantitative approximation results for complex-valued neural networks
Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for approximating $C^n$ functions on compact subsets of $\mathbb{C}^d$ by complex-valued neural networks that employ the modReLU activation function, given by $\sigma(z) = \mathrm{ReLU}(|z| - 1) \, \mathrm{sgn} (z)$, which is one of the most popular complex activation functions used in practice. We show that the derived approximation rates are optimal (up to log factors) in the class of modReLU networks with weights of moderate growth.Open AccessQuantitative approximation results for complex-valued neural networks
Until recently, applications of neural networks in machine learning have almost exclusively relied on real-valued networks. It was recently observed, however, that complex-valued neural networks (CVNNs) exhibit superior performance in applications in which the input is naturally complex-valued, such as MRI fingerprinting. While the mathematical theory of real-valued networks has, by now, reached some level of maturity, this is far from true for complex-valued networks. In this paper, we analyze the expressivity of complex-valued networks by providing explicit quantitative error bounds for approximating $C^n$ functions on compact subsets of $\mathbb{C}^d$ by complex-valued neural networks that employ the modReLU activation function, given by $\sigma(z) = \mathrm{ReLU}(|z| - 1) \, \mathrm{sgn} (z)$, which is one of the most popular complex activation functions used in practice. We show that the derived approximation rates are optimal (up to log factors) in the class of modReLU networks with weights of moderate growth. - Open Access
- 15 April 2021
- Published by Springer Nature in Discrete & Computational Geometry
- Vol. 65 (4) , 953-998
On Recovery Guarantees for One-Bit Compressed Sensing on Manifolds
This paper studies the problem of recovering a signal from one-bit compressed sensing measurements under a manifold model; that is, assuming that the signal lies on or near a manifold of low intrinsic dimension. We provide a convex recovery method based on the Geometric Multi-Resolution Analysis and prove recovery guarantees with a near-optimal scaling in the intrinsic manifold dimension. Our method is the first tractable algorithm with such guarantees for this setting. The results are complemented by numerical experiments confirming the validity of our approach.
- 15 April 2021
- Published by Springer Nature in Discrete & Computational Geometry
- Vol. 65 (4) , 953-998
Open AccessOn Recovery Guarantees for One-Bit Compressed Sensing on Manifolds
This paper studies the problem of recovering a signal from one-bit compressed sensing measurements under a manifold model; that is, assuming that the signal lies on or near a manifold of low intrinsic dimension. We provide a convex recovery method based on the Geometric Multi-Resolution Analysis and prove recovery guarantees with a near-optimal scaling in the intrinsic manifold dimension. Our method is the first tractable algorithm with such guarantees for this setting. The results are complemented by numerical experiments confirming the validity of our approach.