Семинар HDI Lab: Sample complexity of learning a manifold with an unknown dimension, Nikita Puchkin (HSE University)
On December 3 there will be a talk "Sample complexity of learning a manifold with an unknown dimension" by Nikita Puchkin (Junior Research Fellow of HDI Lab NRU HSE).
Abstract: I will discuss the problem of learning a manifold from noisy observations in the case when the dimension of the true manifold is unknown. Many manifold learning procedures require the intrinsic dimension of the data as an input parameter. However, the existing literature provides theoretical guarantees on the dimension estimation only in the case, when the data lies exactly on the manifold. We study an algorithm, which adaptively chooses the manifold’s dimension and has an optimal sample complexity in terms of the Hausdorff loss. Besides, the procedure produces a manifold, such that its curvature does not exceed the curvature of the true manifold too much.
Time: December 3, 2019 05:00pm - 07:00pm
Location: room R204, Pokrovsky Boulevard, 11
If you need a pass to the building please contact Vlada Kuznetsova (firstname.lastname@example.org) with your full name datails.