Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets
Arthur da Cunha, Université Côte d'Azur, Inria, CNRS, I3S, Aarhus University, Aarhus, Denmark, dac@cs.au.dk, "3026 Francesco d'Amore, Aalto University, Bocconi University, Espoo, Finland, francesco.damore@aalto.fi "3026 Emanuele Natale, Université Côte d'Azur, Inria, CNRS, I3S, Sophia Antipolis, France, emanuele.natale@inria.fr
–Neural Information Processing Systems
The left side shows the effect of pruning of neurons in the weight-matrix of afully-connected layer. The rows in white correspond to neurons pruned in theassociated layer while thecolumns inwhite represent theeffectofremoving neurons from the previous layers. On the right, we allude to the possibility of collapsing the pruned matrix into a smaller,denseone.
Neural Information Processing Systems
Feb-19-2026, 11:24:40 GMT
- Country:
- North America
- United States
- Maryland > Baltimore (0.04)
- Washington > King County
- Seattle (0.04)
- Texas > Travis County
- Austin (0.04)
- New York > New York County
- New York City (0.04)
- Louisiana > Orleans Parish
- New Orleans (0.04)
- Colorado > Denver County
- Denver (0.04)
- Canada > British Columbia
- United States
- Europe
- France (0.04)
- Germany (0.04)
- Finland (0.04)
- Austria (0.04)
- United Kingdom > England
- Cambridgeshire > Cambridge (0.04)
- Spain > Catalonia
- Barcelona Province > Barcelona (0.04)
- Italy
- Denmark > Central Jutland
- Aarhus (0.04)
- North America
- Technology: