McTorch, a manifold optimization library for deep learning
This work addresses the need for accessible tools to incorporate manifold constraints in deep learning applications, though it is incremental as it builds on existing PyTorch infrastructure.
The authors introduced McTorch, a library that extends PyTorch to facilitate manifold optimization in deep learning by decoupling manifold definitions and optimizers, making it easier to apply constraints like orthogonality and rank constraints.
In this paper, we introduce McTorch, a manifold optimization library for deep learning that extends PyTorch. It aims to lower the barrier for users wishing to use manifold constraints in deep learning applications, i.e., when the parameters are constrained to lie on a manifold. Such constraints include the popular orthogonality and rank constraints, and have been recently used in a number of applications in deep learning. McTorch follows PyTorch's architecture and decouples manifold definitions and optimizers, i.e., once a new manifold is added it can be used with any existing optimizer and vice-versa. McTorch is available at https://github.com/mctorch .