Keywords: Parameter symmetry, loss landscapes, identifiability, mode connectivity, optimization
TL;DR: We develop neural network architectures with less parameter-space symmetries, and empirically study the impact of parameter symmetries on various phenomena in deep learning.
Abstract: Many algorithms and observed phenomena in deep learning appear to be affected by parameter symmetries --- transformations of neural network parameters that do not change the underlying neural network function. These include linear mode connectivity, model merging, Bayesian neural network inference, metanetworks, and several other characteristics of optimization or loss-landscapes. In this work, we empirically investigate the impact of neural parameter symmetries by introducing new neural network architectures that have reduced parameter space symmetries. We develop two methods, with some provable guarantees, of modifying standard neural networks to reduce parameter space symmetries. With these new methods, we conduct a comprehensive experimental study consisting of multiple tasks aimed at assessing the effect of removing parameter symmetries. Our experiments reveal several interesting observations on the empirical impact of parameter symmetries; for instance, we observe linear mode connectivity and monotonic linear interpolation in our networks, without any alignment of weight spaces.
Student Paper: Yes
Submission Number: 37
Loading