Search Results for author:
Found 57 papers, 24 papers with code
How To Make Your Cell Tracker Say "I dunno!"
Cell tracking is a key computational task in live-cell microscopy, but fully automated analysis of high-throughput imaging requires reliable and, thus, uncertainty-aware data analysis tools, as the amount of data recorded within a single experiment exceeds what humans are able to overlook.
Paths and Ambient Spaces in Neural Loss Landscapes
Understanding the structure of neural network loss surfaces, particularly the emergence of low-loss tunnels, is critical for advancing neural network theory and practice.
Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
To tackle these challenges, we introduce an ensembling approach that leverages strategies from optimization and a recently proposed sampler called Microcanonical Langevin Monte Carlo (MCLMC) for efficient, robust and predictable sampling performance.
Calibrating LLMs with Information-Theoretic Evidential Deep Learning
Fine-tuned large language models (LLMs) often exhibit overconfidence, particularly when trained on small datasets, resulting in poor calibration and inaccurate uncertainty estimates.
Deep Weight Factorization: Sparse Learning Through the Lens of Artificial Symmetries
Sparse regularization techniques are well-established in machine learning, yet their application in neural networks remains challenging due to the non-differentiability of penalties like the $L_1$ norm, which is incompatible with stochastic gradient descent.
Can Transformers Learn Full Bayesian Inference in Context?
Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities.
A Functional Extension of Semi-Structured Networks
Semi-structured networks (SSNs) merge the structures familiar from additive models with deep neural networks, allowing the modeling of interpretable partial feature effects while capturing higher-order non-linearities at the same time.
Achieving interpretable machine learning by functional decomposition of black-box models into explainable predictor effects
Our method is based on a novel concept termed stacked orthogonality, which ensures that the main effects capture as much functional behavior as possible and do not contain information explained by higher-order interactions.
How Inverse Conditional Flows Can Serve as a Substitute for Distributional Regression
Neural network representations of simple models, such as linear regression, are being studied increasingly to better understand the underlying principles of deep learning algorithms.
Generalizing Orthogonalization for Models with Non-Linearities
The complexity of black-box algorithms can lead to various challenges, including the introduction of biases.
Position: Why We Must Rethink Empirical Research in Machine Learning
We warn against a common but incomplete understanding of empirical research in machine learning that leads to non-replicable results, makes findings unreliable, and threatens to undermine progress in the field.
Post-Training Network Compression for 3D Medical Image Segmentation: Reducing Computational Efforts via Tucker Decomposition
The application of Tucker decomposition to the TS model substantially reduced the model parameters and FLOPs across various compression rates, with limited loss in segmentation accuracy.
On Training Survival Models with Scoring Rules
Empirical comparisons on synthetic and real-world data indicate that scoring rules can be successfully incorporated into model training and yield competitive predictive performance with established time-to-event models.
Interpretable Machine Learning for TabPFN
The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes.
Scalable Higher-Order Tensor Product Spline Models
In the current era of vast data and transparent machine learning, it is essential for techniques to operate at a large scale while providing a clear mathematical comprehension of the internal workings of the method.
Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
A major challenge in sample-based inference (SBI) for Bayesian neural networks is the size and structure of the networks' parameter space.
Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI
In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets.
Bayesian Semi-structured Subspace Inference
To this end, we extend subspace inference for joint posterior sampling from a full parameter space for structured effects and a subspace for unstructured effects.
Post-hoc Orthogonalization for Mitigation of Protected Feature Bias in CXR Embeddings
Methods: An orthogonalization is utilized to remove the influence of protected features (e. g., age, sex, race) in CXR embeddings, ensuring feature-independent results.
Baby's CoThought: Leveraging Large Language Models for Enhanced Reasoning in Compact Models
Large Language Models (LLMs) demonstrate remarkable performance on a variety of natural language understanding (NLU) tasks, primarily due to their in-context learning ability.
Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
Additionally, our theory establishes results of independent interest regarding matching local minima for arbitrary, potentially unregularized, objectives.
A New PHO-rmula for Improved Performance of Semi-Structured Networks
Recent advances to combine structured regression models and deep neural networks for better interpretability, more expressiveness, and statistically valid uncertainty quantification demonstrate the versatility of semi-structured neural networks (SSNs).
Constrained Probabilistic Mask Learning for Task-specific Undersampled MRI Reconstruction
Undersampling is a common method in Magnetic Resonance Imaging (MRI) to subsample the number of data points in k-space, reducing acquisition times at the cost of decreased image quality.
Fusing Structure from Motion and Simulation-Augmented Pose Regression from Optical Flow for Challenging Indoor Environments
In this work, we propose recurrent fusion networks to optimally align absolute and relative pose predictions to improve the absolute pose prediction.
Towards Efficient MCMC Sampling in Bayesian Neural Networks by Exploiting Symmetry
Bayesian inference in deep neural networks is challenging due to the high-dimensional, strongly multi-modal parameter posterior density landscape.
Cascaded Latent Diffusion Models for High-Resolution Chest X-ray Synthesis
While recent advances in large-scale foundational models show promising results, their application to the medical domain has not yet been explored in detail.
Representation Learning for Tablet and Paper Domain Adaptation in Favor of Online Handwriting Recognition
The goal of domain adaptation (DA) is to mitigate this domain shift problem by searching for an optimal feature transformation to learn a domain-invariant representation.
Uncertainty-aware predictive modeling for fair data-driven decisions
Both industry and academia have made considerable progress in developing trustworthy and responsible machine learning (ML) systems.
What cleaves? Is proteasomal cleavage prediction reaching a ceiling?
While direct identification of proteasomal cleavage \emph{in vitro} is cumbersome and low throughput, it is possible to implicitly infer cleavage events from the termini of MHC-presented epitopes, which can be detected in large amounts thanks to recent advances in high-throughput MHC ligandomics.
Privacy-Preserving and Lossless Distributed Estimation of High-Dimensional Generalized Additive Mixed Models
In this paper, we propose an algorithm for a distributed, privacy-preserving, and lossless estimation of generalized additive mixed models (GAMM) using component-wise gradient boosting (CWB).
ARMA Cell: A Modular and Effective Approach for Neural Autoregressive Modeling
In this work, we introduce the ARMA cell, a simpler, modular, and effective approach for time series modeling in neural networks.
Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression
We show accuracy improvements for the APR-RPR task and for the RPR-RPR task for aerial vehicles and hand-held devices.
Uncertainty-aware Evaluation of Time-Series Classification for Online Handwriting Recognition with Domain Shift
For many applications, analyzing the uncertainty of a machine learning model is indispensable.
Additive Higher-Order Factorization Machines
One of the main limitations are missing interactions in these models, which are not included for the sake of better interpretability, but also due to untenable computational costs.
Factorized Structured Regression for Large-Scale Varying Coefficient Models
Here, we propose Factorized Structured Regression (FaStR) for scalable varying coefficient models.
Domain Adaptation for Time-Series Classification to Mitigate Covariate Shift
To mitigate this domain shift problem, domain adaptation (DA) techniques search for an optimal transformation that converts the (current) input data from a source domain to a target domain to learn a domain-invariant representation that reduces domain discrepancy.
Auxiliary Cross-Modal Representation Learning with Triplet Loss Functions for Online Handwriting Recognition
We perform extensive evaluations on synthetic image and time-series data, and on data for offline handwriting recognition (HWR) and on online HWR from sensor-enhanced pens for classifying written words.
Benchmarking Online Sequence-to-Sequence and Character-based Handwriting Recognition from IMU-Enhanced Pens
While there exist many offline HWR datasets, there is only little data available for the development of OnHWR methods on paper as it requires hardware-integrated pens.
DeepPAMM: Deep Piecewise Exponential Additive Mixed Models for Complex Hazard Structures in Survival Analysis
Survival analysis (SA) is an active field of research that is concerned with time-to-event outcomes and is prevalent in many domains, particularly biomedical applications.
Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach
Europe was hit by several, disastrous heat and drought events in recent summers.
Survival-oriented embeddings for improving accessibility to complex data structures
We propose a hazard-regularized variational autoencoder that supports straightforward interpretation of deep neural architectures in the context of survival analysis, a field highly relevant in healthcare.
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
The application of deep learning in survival analysis (SA) allows utilizing unstructured and high-dimensional data types uncommon in traditional survival methods.
Probabilistic Time Series Forecasts with Autoregressive Transformation Models
Probabilistic forecasting of time series is an important matter in many applications and research fields.
Accelerated Componentwise Gradient Boosting using Efficient Data Representation and Momentum-based Optimization
Componentwise boosting (CWB), also known as model-based boosting, is a variant of gradient boosting that builds on additive models as base learners to ensure interpretability.
Automatic Componentwise Boosting: An Interpretable AutoML System
Despite its restriction to an interpretable model space, our system is competitive in terms of predictive performance on most data sets while being more user-friendly and transparent.
Developing Open Source Educational Resources for Machine Learning and Data Science
It should be openly accessible to everyone, with as few barriers as possible; even more so for key technologies such as Machine Learning (ML) and Data Science (DS).
deepregression: a Flexible Neural Network Framework for Semi-Structured Deep Distributional Regression
In this paper we describe the implementation of semi-structured deep distributional regression, a flexible framework to learn conditional distributions based on the combination of additive regression models and deep networks.
Deep Semi-Supervised Learning for Time Series Classification
Based on these adaptations, we explore the potential of deep semi-supervised learning in the context of time series classification by evaluating our methods on large public time series classification problems with varying amounts of labelled samples.
Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany
The results corroborate the necessity of including mobility data and showcase the flexibility and interpretability of our approach.
Semi-Structured Deep Piecewise Exponential Models
We propose a versatile framework for survival analysis that combines advanced concepts from statistics with deep learning.
Deep Conditional Transformation Models
Learning the cumulative distribution function (CDF) of an outcome variable conditional on a set of features remains challenging, especially in high-dimensional settings.
Neural Mixture Distributional Regression
We present neural mixture distributional regression (NMDR), a holistic framework to estimate complex finite mixtures of distributional regressions defined by flexible additive predictors.
A General Machine Learning Framework for Survival Analysis
The modeling of time-to-event data, also known as survival analysis, requires specialized methods that can deal with censoring and truncation, time-varying features and effects, and that extend to settings with multiple competing events.
Semi-Structured Distributional Regression -- Extending Structured Additive Models by Arbitrary Deep Neural Networks and Data Modalities
We propose a general framework to combine structured regression models and deep neural networks into a unifying network architecture.
Inference for $L_2$-Boosting
We propose a statistical inference framework for the component-wise functional gradient descent algorithm (CFGD) under normality assumption for model errors, also known as $L_2$-Boosting.
Boosting Functional Regression Models with FDboost
In addition to mean regression, quantile regression models as well as generalized additive models for location scale and shape can be fitted with FDboost.
Computation
Boosting Factor-Specific Functional Historical Models for the Detection of Synchronisation in Bioelectrical Signals
The link between different psychophysiological measures during emotion episodes is not well understood.
