User profiles for Felix Divo

Felix Divo

TU Darmstadt, Germany
Verified email at cs.tu-darmstadt.de
Cited by 748

Tslearn, a machine learning toolkit for time series data

R Tavenard, J Faouzi, G Vandewiele, F Divo… - Journal of machine …, 2020 - jmlr.org
tslearn is a general-purpose Python machine learning library for time series that offers tools
for pre-processing and feature extraction as well as dedicated models for clustering, …

Forecasting Company Fundamentals

F Divo, E Endress, K Endler, K Kersting… - arXiv preprint arXiv …, 2024 - arxiv.org
Company fundamentals are key to assessing companies' financial and overall success and
stability. Forecasting them is important in multiple fields, including investing and …

The Constitutional Filter

S Kohaut, F Divo, B Flade, DS Dhami, J Eggert… - arXiv preprint arXiv …, 2024 - arxiv.org
Predictions in environments where a mix of legal policies, physical limitations, and
operational preferences impacts an agent's motion are inherently difficult. Since Neuro-Symbolic …

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation

D Steinmann, F Divo, M Kraus, A Wüst… - arXiv preprint arXiv …, 2024 - arxiv.org
Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders,
present a significant challenge in machine learning and AI, critically affecting model …

United We Pretrain, Divided We Fail! Representation Learning for Time Series by Pretraining on 75 Datasets at Once

M Kraus, F Divo, D Steinmann, DS Dhami… - arXiv preprint arXiv …, 2024 - arxiv.org
In natural language processing and vision, pretraining is utilized to learn effective representations.
Unfortunately, the success of pretraining does not easily carry over to time series due …

Graph Neural Networks Need Cluster-Normalize-Activate Modules

A Skryagin, F Divo, MA Ali, DS Dhami… - arXiv preprint arXiv …, 2024 - arxiv.org
Graph Neural Networks (GNNs) are non-Euclidean deep learning models for graph-structured
data. Despite their successful and diverse applications, oversmoothing prohibits deep …

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

M Kraus, F Divo, DS Dhami, K Kersting - arXiv preprint arXiv:2410.16928, 2024 - arxiv.org
Time series data is prevalent across numerous fields, necessitating the development of robust
and accurate forecasting models. Capturing patterns both within and between temporal …

Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data

H Poonia, F Divo, K Kersting, DS Dhami - arXiv preprint arXiv:2502.09981, 2025 - arxiv.org
Causality in time series can be difficult to determine, especially in the presence of non-linear
dependencies. The concept of Granger causality helps analyze potential relationships …

probabilists/zuko: Zuko 1.1. 0

F Rozet, F Divo, S Schnake - Zenodo, 2024 - ui.adsabs.harvard.edu
✨ What's new New VAE tutorial using the MNIST dataset (8812e04507bf27d4fb9346acd9174459c097fc62)
Add support for unconditional univariate flows (# 34) New Bernstein …

The influence of divorce on men's health

DS Felix, WD Robinson, KJ Jarzynka - Journal of Men's Health, 2013 - liebertpub.com
… In this case report we review current literature on the sequelae of divorce on men's health,
and highlight key features of divorce from a multi-disciplinary lens using the example of a 45-…