15 citations · 28 across the 2 of their papers we have counts for
4 papers
FlipOut: Uncovering Redundant Weights via Sign Flipping
Andrei Apostol, Maarten Stol, Patrick Forré
Modern neural networks, although achieving state-of-the-art results on many tasks, tend to have a large number of parameters, which increases training time and resource usage. This…
Pruning via Iterative Ranking of Sensitivity Statistics
Stijn Verdenius, Maarten Stol, Patrick Forré
With the introduction of SNIP [arXiv:1810.02340v2], it has been demonstrated that modern neural networks can effectively be pruned before training. Yet, its sensitivity criterion h…
Neural Ordinary Differential Equations on Manifolds
Luca Falorsi, Patrick Forré
Normalizing flows are a powerful technique for obtaining reparameterizable samples from complex multimodal distributions. Unfortunately current approaches fall short when the under…
Cohomological Hasse principle for schemes over valuation rings of higher dimensional local fields
Patrick Forré
K. Kato's conjecture about the cohomological Hasse principle for regular connected schemes which are flat and proper over the complete discrete valuation rings $\math…