2021
Statistical mechanical analysis of neural network pruning
UAI 2021poster
Deep learning architectures with a huge number of parameters are often compressed using
3 accepted papers
Deep learning architectures with a huge number of parameters are often compressed using
Sensory processing is often characterized as implementing probabilistic inference: networks of neurons compute posterior beliefs over unobserved causes given the sensory inputs. How these beliefs are computed and represented by neural responses is much-debated (Fiser et al. 2010, Pouget et al. 2013)…
We introduce a unifying generalization of the Lovász theta function, and the associated geometric embedding, for graphs with weights on both nodes and edges. We show how it can be computed exactly by semidefinite programming, and how to approximate it using SVM computations. We show how the theta fu…