← Search

Stephane Rivaud

2 accepted papers

2025

PETRA: Parallel End-to-end Training with Reversible Architectures

ICLR 2025spotlight

Reversible architectures have been shown to be capable of performing on par with their non-reversible architectures, being applied in deep learning for memory savings and generative modeling. In this work, we show how reversible architectures can solve challenges in parallelizing deep model training…

Cited by 0SourcePDFScholar
2023

Can Forward Gradient Match Backpropagation?

ICML 2023poster

Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding problems generally associated with backpropagation gradient computation, such as locking and memorization requirements.…