5 citations · 11 across the 6 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023★ 4 cited
Robust low-rank training via approximate orthonormal constraints
Dayana Savostianova, Emanuele Zangrando, Gianluca Ceruti +1
With the growth of model and data sizes, a broad effort has been made to design pruning techniques that reduce the resource demand of deep learning pipelines, while retaining model…
cs.LG2023★ 1 cited
Geometry-aware training of factorized layers in tensor Tucker format
Emanuele Zangrando, Steffen Schotthöfer, Gianluca Ceruti +2
Reducing parameter redundancies in neural network architectures is crucial for achieving feasible computational and memory requirements during training and inference phases. Given…