More Like this

1. Product Manifold Learning

   Zhang, Sharon; Moscovich, Amit; Singer, Amit (January 2021, Proceedings of Machine Learning Research)

   Banerjee, Arindam; Fukumizu, Kenji (Ed.)
2. Equivariant Manifold Flows

   Isay Katsman, Aaron Lou (December 2021, Advances in neural information processing systems)

   Ranzato, M.; Beygelzimer, A.; Dauphin, Y.; Liang, P.S.; Wortman Vaughan, J. (Ed.)

   Tractably modelling distributions over manifolds has long been an important goal in the natural sciences. Recent work has focused on developing general machine learning models to learn such distributions. However, for many applications these distributions must respect manifold symmetries—a trait which most previous models disregard. In this paper, we lay the theoretical foundations for learning symmetry-invariant distributions on arbitrary manifolds via equivariant manifold flows. We demonstrate the utility of our approach by learning quantum field theory-motivated invariant SU(n) densities and by correcting meteor impact dataset bias. 

   more » « less
3. Deep Manifold Prior

   https://doi.org/10.1109/ICCVW54120.2021.00130  

   Gadelha, Matheus; Wang, Rui; Maji, Subhransu (October 2021, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops)
4. The sparse manifold transform

   Chen, Yubei; Paiton, Dylan M.; Olshausen, Bruno A. (September 2019, Advances in neural information processing systems)
5. Manifold filter-combine networks

   https://doi.org/10.1007/s43670-025-00115-2  

   Johnson, David R; Chew, Joyce A; Viswanath, Siddharth; Brouwer, Edward De; Needell, Deanna; Krishnaswamy, Smita; Perlmutter, Michael (December 2025, Sampling Theory, Signal Processing, and Data Analysis)

   Abstract In order to better understand manifold neural networks (MNNs), we introduce Manifold Filter-Combine Networks (MFCNs). Our filter-combine framework parallels the popular aggregate-combine paradigm for graph neural networks (GNNs) and naturally suggests many interesting families of MNNs which can be interpreted as manifold analogues of various popular GNNs. We propose a method for implementing MFCNs on high-dimensional point clouds that relies on approximating an underlying manifold by a sparse graph. We then prove that our method is consistent in the sense that it converges to a continuum limit as the number of data points tends to infinity, and we numerically demonstrate its effectiveness on real-world and synthetic data sets. 

   more » « less