Conic Linear Units: Orthogonal Equivariance Improves General-Purpose Nonlinearities

Changqing Fu

Keywords: Neural Network Architectures, Activation Functions

TL;DR: This paper introduces a novel activation function that enhances the symmetry of neural networks and improves performance across a variety of models.

Abstract: Most activation functions operate component-wise, which restricts the equivariance of neural networks to permutations. We introduce Conic Linear Units (CoLU) and generalize the symmetry of neural networks to continuous orthogonal groups. By interpreting ReLU as a projection onto its invariant set—the positive orthant—we propose a conic activation function that uses a Lorentz cone instead. Its performance can be further improved by considering multi-head structures, soft scaling, and axis sharing. CoLU associated with low-dimensional cones outperforms the component-wise ReLU in a wide range of models—including MLP, ResNet, and UNet, etc., achieving better loss values and faster convergence. It significantly improves diffusion models' training and performance. CoLU originates from a first-principles approach to various forms of neural networks and fundamentally changes their algebraic structure.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 7008