Search Results for author:
Found 4 papers, 2 papers with code
Symmetries, flat minima, and the conserved quantities of gradient flow
Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys.
Quiver neural networks
We develop a uniform theoretical approach towards the analysis of various neural network connectivity architectures by introducing the notion of a quiver neural network.
Model Compression via Symmetries of the Parameter Space
We provide a theoretical framework for neural networks in terms of the representation theory of quivers, thus revealing symmetries of the parameter space of neural networks.
Universal approximation and model compression for radial neural networks
We introduce a class of fully-connected neural networks whose activation functions, rather than being pointwise, rescale feature vectors by a function depending only on their norm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
