Search Results for author: Thomas Kneib

Found 12 papers, 8 papers with code

Distributional Gradient Boosting Machines

2 code implementations2 Apr 2022 Alexander März, Thomas Kneib

We present a unified probabilistic gradient boosting framework for regression tasks that models and predicts the entire conditional distribution of a univariate response variable as a function of covariates.

Prediction Intervals regression

Twitmo: A Twitter Data Topic Modeling and Visualization Package for R

1 code implementation8 Jul 2022 Andreas Buchmüller, Gillian Kant, Christoph Weisser, Benjamin Säfken, Krisztina Kis-Katos, Thomas Kneib

We present Twitmo, a package that provides a broad range of methods to collect, pre-process, analyze and visualize geo-tagged Twitter data.

Information Retrieval Topic Models

Spike-and-Slab Priors for Function Selection in Structured Additive Regression Models

1 code implementation26 May 2011 Fabian Scheipl, Ludwig Fahrmeir, Thomas Kneib

Structured additive regression provides a general framework for complex Gaussian and non-Gaussian regression models, with predictors comprising arbitrary combinations of nonlinear functions and surfaces, spatial effects, varying coefficients, random effects and further regression terms.

Methodology Applications

Neural Additive Models for Location Scale and Shape: A Framework for Interpretable Neural Regression Beyond the Mean

1 code implementation27 Jan 2023 Anton Thielmann, René-Marcel Kruse, Thomas Kneib, Benjamin Säfken

We propose Neural Additive Models for Location Scale and Shape (NAMLSS), a modelling framework that combines the predictive power of classical deep learning models with the inherent advantages of distributional regression while maintaining the interpretability of additive models.

Additive models

Boosting Joint Models for Longitudinal and Time-to-Event Data

1 code implementation9 Sep 2016 Elisabeth Waldmann, David Taylor-Robinson, Nadja Klein, Thomas Kneib, Tania Pressler, Matthias Schmid, Andreas Mayr

Joint Models for longitudinal and time-to-event data have gained a lot of attention in the last few years as they are a helpful technique to approach common a data structure in clinical studies where longitudinal outcomes are recorded alongside event times.

Variable Selection

Probabilistic Topic Modelling with Transformer Representations

1 code implementation6 Mar 2024 Arik Reuter, Anton Thielmann, Christoph Weisser, Benjamin Säfken, Thomas Kneib

With the rise of transformers in Natural Language Processing, however, several successful models that rely on straightforward clustering approaches in transformer-based embedding spaces have emerged and consolidated the notion of topics as clusters of embedding vectors.

Adaptive shrinkage of smooth functional effects towards a predefined functional subspace

no code implementations14 Jan 2021 Paul Wiemann, Thomas Kneib

In this paper, we propose a new horseshoe-type prior hierarchy for adaptively shrinking spline-based functional effects towards a predefined vector space of parametric functions.

Methodology

Bayesian Conditional Transformation Models

no code implementations20 Dec 2020 Manuel Carlan, Thomas Kneib, Nadja Klein

A simulation study demonstrates the competitiveness of our approach against its likelihood-based counterpart but also Bayesian additive models of location, scale and shape and Bayesian quantile regression.

Methodology

Coherence-Based Document Clustering

no code implementations29 Sep 2021 Anton Frederik Thielmann, Christoph Weisser, Thomas Kneib, Benjamin Saefken

While these algorithms differ in their modeling approach, they have in common that hyperparameter optimization is difficult and is mainly achieved by maximizing the extracted topic coherence scores via a grid search.

Clustering Hyperparameter Optimization +1

Bayesian Discrete Conditional Transformation Models

1 code implementation17 May 2022 Manuel Carlan, Thomas Kneib

For count responses, the resulting transformation model is novel in the sense that it is a Bayesian fully parametric yet distribution-free approach that can additionally account for excess zeros with additive transformation function specifications.

Cannot find the paper you are looking for? You can Submit a new open access paper.