How to fit a manifold?
This is a quick introduction of manifold fitting. A PDF version is also available. More details can be found in:
- Fefferman, C., Ivanov, S., Kurylev, Y., Lassas, M., & Narayanan, H. (2018, July). Fitting a putative manifold to noisy data. In Conference On Learning Theory (pp. 688-720). PMLR.
- Yao, Z., & Xia, Y. (2019). Manifold fitting under unbounded noise. arXiv preprint arXiv:1909.10228.
- Yao, Z., Su, J., Li, B., & Yau, S. T. (2023). Manifold fitting. arXiv preprint arXiv:2304.07680.
Method
Let

This pushing process involves two key components: direction and distance. The direction should be perpendicular to
Estimate Direction from Local ‘‘Covariance’’
For each point
to represent the projection matrix onto this space. This projection matrix can be estimated from the local variation centered at

Let
: is roughly in the order of ; : is roughly bounded above by the order of .
Thus, we can define
Then perform SVD on
Smoothing System
To make the overall estimation smooth enough, the weight function for
where
where
The Manifold Estimator
The vector from
which can be shown
close to ;- Jacobian matrix of
is close to , i.e. ; - Hessian matrix of
is lower bounded.

Finally, the manifold estimator is given by
Under all the error bounds and all the smoothness, for any
is close to ;- in its neighborhood,
is rank .
Hence, with high probability,
Enjoy Reading This Article?
Here are some more articles you might like to read next: