Learning a Lie Algebra from Unlabeled Data Pairs
release_nhwcfnffyjgk3mosmiijmpvr3y
by
Chris Ick, Vincent Lostanlen
2020
Abstract
Deep convolutional networks (convnets) show a remarkable ability to learn
disentangled representations. In recent years, the generalization of deep
learning to Lie groups beyond rigid motion in ℝ^n has allowed to
build convnets over datasets with non-trivial symmetries, such as patterns over
the surface of a sphere. However, one limitation of this approach is the need
to explicitly define the Lie group underlying the desired invariance property
before training the convnet. Whereas rotations on the sphere have a well-known
symmetry group (SO(3)), the same cannot be said of many real-world
factors of variability. For example, the disentanglement of pitch, intensity
dynamics, and playing technique remains a challenging task in music information
retrieval.
This article proposes a machine learning method to discover a nonlinear
transformation of the space ℝ^n which maps a collection of
n-dimensional vectors (x_i)_i onto a collection of target
vectors (y_i)_i. The key idea is to approximate every target
y_i by a matrix–vector product of the form
y_i = ϕ(t_i) x_i, where
the matrix ϕ(t_i) belongs to a one-parameter subgroup of
GL_n (ℝ). Crucially, the value of the parameter t_i ∈ℝ may change between data pairs (x_i,
y_i) and does not need to be known in advance.
In text/plain
format
Archived Files and Locations
application/pdf 198.0 kB
file_73pphylghrhizmzdssrgxbvupy
|
arxiv.org (repository) web.archive.org (webarchive) |
2009.09321v1
access all versions, variants, and formats of this works (eg, pre-prints)