A regression approach for explaining manifold embedding coordinates

11/29/2018
by   Marina Meila, et al.
0

Manifold embedding algorithms map high dimensional data, down to coordinates in a much lower dimensional space. One of the aims of the dimension reduction is to find the intrinsic coordinates that describe the data manifold. However, the coordinates returned by the embedding algorithm are abstract coordinates. Finding their physical, domain related meaning is not formalized and left to the domain experts. This paper studies the problem of recovering the domain-specific meaning of the new low dimensional representation in a semi-automatic, principled fashion. We propose a method to explain embedding coordinates on a manifold as non-linear compositions of functions from a user-defined dictionary. We show that this problem can be set up as a sparse linear Group Lasso recovery problem, find sufficient recovery conditions, and demonstrate its effectiveness on data.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/01/2023

Dictionary-based Manifold Learning

We propose a paradigm for interpretable Manifold Learning for scientific...
research
02/02/2021

Manifold Repairing, Reconstruction and Denoising from Scattered Data in High-Dimension

We consider a problem of great practical interest: the repairing and rec...
research
07/02/2019

Selecting the independent coordinates of manifolds with large aspect ratios

Many manifold embedding algorithms fail apparently when the data manifol...
research
05/18/2019

A Discrete Empirical Interpolation Method for Interpretable Immersion and Embedding of Nonlinear Manifolds

Manifold learning techniques seek to discover structure-preserving mappi...
research
04/15/2020

LOCA: LOcal Conformal Autoencoder for standardized data coordinates

We propose a deep-learning based method for obtaining standardized data ...
research
05/22/2020

Data-driven Efficient Solvers and Predictions of Conformational Transitions for Langevin Dynamics on Manifold in High Dimensions

We work on dynamic problems with collected data {x_i} that distributed o...
research
06/14/2021

Full interpretable machine learning in 2D with inline coordinates

This paper proposed a new methodology for machine learning in 2-dimensio...

Please sign up or login with your details

Forgot password? Click here to reset