McTorch, a manifold optimization library for deep learning
arXiv:1810.01811
Abstract
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 .
References in corpus (6)
- Manopt, a Matlab toolbox for optimization on manifolds
- Nonconvex phase synchronization
- Near-optimal bounds for phase synchronization
- Riemannian stochastic variance reduced gradient algorithm with retraction and vector transport
- Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
- Symmetry-invariant optimization in deep networks
Cited by in corpus (8)
- Geoopt: Riemannian Optimization in PyTorch
- Riemannian adaptive stochastic gradient algorithms on matrix manifolds
- Sliced Gromov-Wasserstein
- Manifolds.jl: An Extensible Julia Framework for Data Analysis on Manifolds
- On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
- A contribution to Optimal Transport on incomparable spaces
- Manifold optimization for non-linear optimal transport problems
- Tangent Space Backpropagation for 3D Transformation Groups