Skip to yearly menu bar Skip to main content


Improving Convergence and Generalization Using Parameter Symmetries

Bo Zhao · Robert M. Gower · Robin Walters · Rose Yu

Halle B #206
[ ]
Wed 8 May 1:45 a.m. PDT — 3:45 a.m. PDT
Oral presentation: Oral 3C
Wed 8 May 1 a.m. PDT — 1:45 a.m. PDT


In many neural networks, different values of the parameters may result in the same loss value. Parameter space symmetries are loss-invariant transformations that change the model parameters. Teleportation applies such transformations to accelerate optimization. However, the exact mechanism behind this algorithm's success is not well understood. In this paper, we show that teleportation not only speeds up optimization in the short-term, but gives overall faster time to convergence. Additionally, teleporting to minima with different curvatures improves generalization, which suggests a connection between the curvature of the minimum and generalization ability. Finally, we show that integrating teleportation into a wide range of optimization algorithms and optimization-based meta-learning improves convergence. Our results showcase the versatility of teleportation and demonstrate the potential of incorporating symmetry in optimization.

Chat is not available.