6 papers
Physiome-ODE: A Benchmark for Irregularly Sampled Multivariate Time Series Forecasting Based on Biological ODEs
Christian Klötergens, Vijaya Krishna Yalavarthi, Randolf Scholz +3
State-of-the-art methods for forecasting irregularly sampled time series with missing values predominantly rely on just four datasets and a few small toy examples for evaluation. W…
Channel Dependence, Limited Lookback Windows, and the Simplicity of Datasets: How Biased is Time Series Forecasting?
Ibram Abdelmalak, Kiran Madhusudhanan, Jungmin Choi +4
In Long-term Time Series Forecasting (LTSF), the lookback window is a critical hyperparameter often set arbitrarily, undermining the validity of model evaluations. We argue that th…
STADE: Standard Deviation as a Pruning Metric
Diego Coello de Portugal Mecke, Haya Alyoussef, Maximilian Stubbemann +3
Recently, Large Language Models (LLMs) have become very widespread and are used to solve a wide variety of tasks. To successfully handle these tasks, LLMs require longer training t…
TabResFlow: A Normalizing Spline Flow Model for Probabilistic Univariate Tabular Regression
Kiran Madhusudhanan, Vijaya Krishna Yalavarthi, Jonas Sonntag +2
Tabular regression is a well-studied problem with numerous industrial applications, yet most existing approaches focus on point estimation, often leading to overconfident predictio…
A Cross-Domain Benchmark for Active Learning
Thorben Werner, Johannes Burchert, Maximilian Stubbemann +1
Active Learning (AL) deals with identifying the most informative samples for labeling to reduce data annotation costs for supervised learning tasks. AL research suffers from the fa…
Functional Latent Dynamics for Irregularly Sampled Time Series Forecasting
Christian Klötergens, Vijaya Krishna Yalavarthi, Maximilian Stubbemann +1
Irregularly sampled time series with missing values are often observed in multiple real-world applications such as healthcare, climate and astronomy. They pose a significant challe…