3 papers
cs.LG2024
AutoPQ: Automating Quantile estimation from Point forecasts in the context of sustainability
Stefan Meisenbacher, Kaleb Phipps, Oskar Taubert +4
Optimizing smart grid operations relies on critical decision-making informed by uncertainty quantification, making probabilistic forecasting a vital tool. Designing such forecastin…
cs.LG2024
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…
cs.LG2024
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…