150 citations · 423 across the 23 of their papers we have counts for
23 papers
Float8@2bits: Entropy Coding Enables Data-Free Model Compression
Patrick Putzky, Martin Genzel, Mattes Mollenhauer +3
Post-training compression is currently divided into two contrasting regimes. On the one hand, fast, data-free, and model-agnostic methods (e.g., NF4 or HQQ) offer maximum accessibi…
Choose Your Model Size: Any Compression of Large Language Models Without Re-Computation
Martin Genzel, Patrick Putzky, Pengfei Zhao +5
The adoption of Foundation Models in resource-constrained environments remains challenging due to their large size and inference costs. A promising way to overcome these limitation…
Self-Distilled Representation Learning for Time Series
Felix Pieper, Konstantin Ditschuneit, Martin Genzel +2
Self-supervised learning for time-series data holds potential similar to that recently unleashed in Natural Language Processing and Computer Vision. While most existing works in th…
Memorization With Neural Nets: Going Beyond the Worst Case
Sjoerd Dirksen, Patrick Finke, Martin Genzel
In practice, deep neural networks are often able to easily interpolate their training data. To understand this phenomenon, many works have aimed to quantify the memorization capaci…
Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models
Julien Siems, Konstantin Ditschuneit, Winfried Ripken +4
Generalized Additive Models (GAMs) have recently experienced a resurgence in popularity due to their interpretability, which arises from expressing the target value as a sum of non…
Let's Enhance: A Deep Learning Approach to Extreme Deblurring of Text Images
Theophil Trippe, Martin Genzel, Jan Macdonald +1
This work presents a novel deep-learning-based pipeline for the inverse problem of image deblurring, leveraging augmentation and pre-training with synthetic data. Our results build…
Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning
Martin Genzel, Ingo Gühring, Jan Macdonald +1
This work is concerned with the following fundamental question in scientific machine learning: Can deep-learning-based methods solve noise-free inverse problems to near-perfect acc…
Gradient-Based Learning of Discrete Structured Measurement Operators for Signal Recovery
Jonathan Sauder, Martin Genzel, Peter Jung
Countless signal processing applications include the reconstruction of signals from few indirect linear measurements. The design of effective measurement operators is typically con…
The Separation Capacity of Random Neural Networks
Sjoerd Dirksen, Martin Genzel, Laurent Jacques +1
Neural networks with random weights appear in a variety of machine learning applications, most prominently as the initialization of many deep learning algorithms and as a computati…
AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
Martin Genzel, Jan Macdonald, Maximilian März
This report is dedicated to a short motivation and description of our contribution to the AAPM DL-Sparse-View CT Challenge (team name: "robust-and-stable"). The task is to recover…
Solving Inverse Problems With Deep Neural Networks -- Robustness Included?
Martin Genzel, Jan Macdonald, Maximilian März
In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems. Before such approaches can find application in safety-critical field…
Compressed Sensing with 1D Total Variation: Breaking Sample Complexity Barriers via Non-Uniform Recovery (iTWIST'20)
Martin Genzel, Maximilian März, Robert Seidel
This paper investigates total variation minimization in one spatial dimension for the recovery of gradient-sparse signals from undersampled Gaussian measurements. Recently establis…
A Unified Approach to Uniform Signal Recovery From Non-Linear Observations
Martin Genzel, Alexander Stollenwerk
Recent advances in quantized compressed sensing and high-dimensional estimation have shown that signal recovery is even feasible under strong non-linear distortions in the observat…
Generic Error Bounds for the Generalized Lasso with Sub-Exponential Data
Martin Genzel, Christian Kipp
This work performs a non-asymptotic analysis of the generalized Lasso under the assumption of sub-exponential data. Our main results continue recent research on the benchmark case…
Compressed Sensing with 1D Total Variation: Breaking Sample Complexity Barriers via Non-Uniform Recovery
Martin Genzel, Maximilian März, Robert Seidel
This paper investigates total variation minimization in one spatial dimension for the recovery of gradient-sparse signals from undersampled Gaussian measurements. Recently establis…
The Mismatch Principle: The Generalized Lasso Under Large Model Uncertainties
Martin Genzel, Gitta Kutyniok
We study the estimation capacity of the generalized Lasso, i.e., least squares minimization combined with a (convex) structural constraint. While Lasso-type estimators were origina…
Robust 1-Bit Compressed Sensing via Hinge Loss Minimization
Martin Genzel, Alexander Stollenwerk
This work theoretically studies the problem of estimating a structured high-dimensional signal from noisy -bit Gaussian measurements. Our recovery approac…
-Analysis Minimization and Generalized (Co-)Sparsity: When Does Recovery Succeed?
Martin Genzel, Gitta Kutyniok, Maximilian März
This paper investigates the problem of signal estimation from undersampled noisy sub-Gaussian measurements under the assumption of a cosparse model. Based on generalized notions of…
Recovering Structured Data From Superimposed Non-Linear Measurements
Martin Genzel, Peter Jung
This work deals with the problem of distributed data acquisition under non-linear communication constraints. More specifically, we consider a model setup where distributed node…
A Mathematical Framework for Feature Selection from Real-World Data with Non-Linear Observations
Martin Genzel, Gitta Kutyniok
In this paper, we study the challenge of feature selection based on a relatively small collection of sample pairs . The observations $y_i \in \mat…
High-Dimensional Estimation of Structured Signals from Non-Linear Observations with General Convex Loss Functions
Martin Genzel
In this paper, we study the issue of estimating a structured signal from non-linear and noisy Gaussian observations. Supposing that is contained in a c…
Sparse Proteomics Analysis - A compressed sensing-based approach for feature selection and classification of high-dimensional proteomics mass spectrometry data
Tim Conrad, Martin Genzel, Nada Cvetkovic +5
Background: High-throughput proteomics techniques, such as mass spectrometry (MS)-based approaches, produce very high-dimensional data-sets. In a clinical setting one is often inte…
Asymptotic Analysis of Inpainting via Universal Shearlet Systems
Martin Genzel, Gitta Kutyniok
Recently introduced inpainting algorithms using a combination of applied harmonic analysis and compressed sensing have turned out to be very successful. One key ingredient is a car…