2 papers
cs.LG2024
Input Space Mode Connectivity in Deep Neural Networks
Jakub Vrabel, Ori Shem-Ur, Yaron Oz +1
We extend the concept of loss landscape mode connectivity to the input space of deep neural networks. Mode connectivity was originally studied within parameter space, where it desc…
cs.LG2024
Weak Correlations as the Underlying Principle for Linearization of Gradient-Based Learning Systems
Ori Shem-Ur, Khen Cohen, Aviv Orly +1
Deep learning models, such as wide neural networks, can be conceptualized as nonlinear dynamical physical systems characterized by a multitude of interacting degrees of freedom. Su…