Papers

Published Papers

The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models
Stephan Rabanser, Tim Januschowski, Valentin Flunkert, David Salinas, Jan Gasthaus
2020
Workshop on Mining and Learning from Time Series at KDD 2020. Selected for oral presentation.
[arXiv][Workshop Paper][Slides]

Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
Stephan Rabanser, Stephan Günnemann, Zachary C. Lipton
2019
Advances in Neural Information Processing Systems (NeurIPS) 2019.
Previoulsy presented at the Workshop on Debugging Machine Learning Models at ICLR 2019.
[arXiv][Slides][Poster]

WIP Papers

Denoising Spectral Clustering Through Latent Data Decomposition
Stephan Rabanser, Oleksandr Shchur, Stephan Günnemann
2018
[PDF]

Improving Online GMM Learning Via Covariance Weighting
Stephan Rabanser, Maksim Greiner
2018
[PDF]

Introduction to Tensor Decompositions and Their Applications in Machine Learning
Stephan Rabanser, Oleksandr Shchur, Stephan Günnemann
2017
[arXiv]

Theses

Detecting Distribution Shifts in Machine Learning
Stephan Rabanser
2019
Master's Thesis.
[PDF]