Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.
Loss landscapes and optimization in over- parameterized non-linear systems and neural networks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Analog-SGD-AP converges with iteration complexity O(ε^{-2} + ε^{-1}) for multi-layer DNNs on AIMC hardware despite analog weight-update imperfections and asynchronous stale gradients.
citing papers explorer
-
Flat Channels to Infinity in Neural Loss Landscapes
Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.
-
On the Convergence Theory of Pipeline Gradient-based Analog In-memory Training
Analog-SGD-AP converges with iteration complexity O(ε^{-2} + ε^{-1}) for multi-layer DNNs on AIMC hardware despite analog weight-update imperfections and asynchronous stale gradients.