A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Complexity from Adaptive-Symmetries Breaking: Global Minima in the Statistical Mechanics of Deep Neural Networks
[article]
2022
Preserved Fulltext
One particular finding is that a hierarchically large DNN would have a large reservoir of adaptive symmetries, and when the information capacity of the reservoir exceeds the complexity of the dataset, ...
The model is analyzed with a method referred as the statistical assembly method that analyzes the coarse-grained behaviors (over a symmetry group) of the heterogeneous hierarchical many-body interaction ...
Storkey, On the relation between the sharpest direc- tions of
Neural Networks with ReLU Activation, in NIPS (2017) DNN loss and the SGD step length, in ICLR (2019). ...
doi:10.48550/arxiv.2201.07934
fatcat:7lir4oz3rzcy5erjx4g5qjv3xy