Skip to yearly menu bar Skip to main content

Virtual oral
Affinity Workshop: Tiny Papers Showcase Day (a DEI initiative)

Geodesic Mode Connectivity

Charlie Tan


Mode connectivity is a phenomenon where trained models are connected by a path of low loss. We reframe this in the context of Information Geometry, where neural networks are studied as spaces of parameterized distributions with curved geometry. We hypothesize that shortest paths in these spaces, known as geodesics, correspond to mode-connecting paths in the loss landscape. We propose an algorithm to approximate geodesics and demonstrate that they achieve mode connectivity.

Chat is not available.