11 citations · 26 across the 18 of their papers we have counts for
5 papers · 1 filter
A Comparative Study of Pruning Methods in Transformer-based Time Series Forecasting
Nicholas Kiefer, Arvid Weyrauch, Muhammed Öz +3
The current landscape in time-series forecasting is dominated by Transformer-based models. Their high parameter count and corresponding demand in computational resources pose a cha…
Beyond Backpropagation: Optimization with Multi-Tangent Forward Gradients
Katharina Flügel, Daniel Coquelin, Marie Weiel +3
The gradients used to train neural networks are typically computed using backpropagation. While an efficient way to obtain exact gradients, backpropagation is computationally expen…
AB-Training: A Communication-Efficient Approach for Distributed Low-Rank Learning
Daniel Coquelin, Katherina Flügel, Marie Weiel +5
Communication bottlenecks severely hinder the scalability of distributed neural network training, particularly in high-performance computing (HPC) environments. We introduce AB-tra…
ReCycle: Fast and Efficient Long Time Series Forecasting with Residual Cyclic Transformers
Arvid Weyrauch, Thomas Steens, Oskar Taubert +6
Transformers have recently gained prominence in long time series forecasting by elevating accuracies in a variety of use cases. Regrettably, in the race for better predictive perfo…
Harnessing Orthogonality to Train Low-Rank Neural Networks
Daniel Coquelin, Katharina Flügel, Marie Weiel +4
This study explores the learning dynamics of neural networks by analyzing the singular value decomposition (SVD) of their weights throughout training. Our investigation reveals tha…