Corpus ID: 211677691

Differentiating through the Fr\'echet Mean

@article{Lou2020DifferentiatingTT,
  title={Differentiating through the Fr\'echet Mean},
  author={Aaron Lou and Isay Katsman and Qingxuan Jiang and Serge J. Belongie and Ser-Nam Lim and Christopher De Sa},
  journal={arXiv: Machine Learning},
  year={2020}
}
Recent advances in deep representation learning on Riemannian manifolds extend classical deep learning operations to better capture the geometry of the manifold. One possible extension is the Frechet mean, the generalization of the Euclidean mean; however, it has been difficult to apply because it lacks a closed form with an easily computable derivative. In this paper, we show how to differentiate through the Frechet mean for arbitrary Riemannian manifolds. Then, focusing on hyperbolic space… Expand
2 Citations

Figures and Tables from this paper

Learning Hyperbolic Representations for Unsupervised 3D Segmentation
  • Highly Influenced
  • PDF
Hyperbolic Deep Neural Networks: A Survey
  • 1
  • Highly Influenced
  • PDF

References

SHOWING 1-10 OF 41 REFERENCES
Riemannian batch normalization for SPD neural networks
  • 16
  • PDF
Hyperbolic Neural Networks
  • 116
  • Highly Influential
  • PDF
Lorentzian Distance Learning for Hyperbolic Representations
  • 16
  • PDF
Trivializations for Gradient-Based Optimization on Manifolds
  • 31
  • PDF
Hyperbolic Graph Convolutional Neural Networks
  • 96
  • Highly Influential
  • PDF
Poincaré Embeddings for Learning Hierarchical Representations
  • 493
  • PDF
Poincaré GloVe: Hyperbolic Word Embeddings
  • 90
  • PDF
Hyperbolic Attention Networks
  • 67
  • PDF
OptNet: Differentiable Optimization as a Layer in Neural Networks
  • 280
  • PDF
Differentiable Convex Optimization Layers
  • 92
  • PDF
...
1
2
3
4
5
...