In this paper, we explore a process called neural teleportation, a mathematical consequence of applying quiver representation theory to neural networks.Neural teleportation teleports a network to a new position in the weight space and preserves its function.This phenomenon comes directly from the definitions of representation theory applied LIP SHINE PEACHY to neural networks and it turns out to be a very simple operation that has remarkable properties.We shed light on the surprising 156 and counter-intuitive consequences neural teleportation has on the loss landscape.
In particular, we show that teleportation can be used to explore loss level curves, that it changes the local loss landscape, sharpens global minima and boosts back-propagated gradients at any moment during the learning process.