On the Limitations of Representing Functions on Sets

01/25/2019
by   Edward Wagstaff, et al.
4

Recent work on the representation of functions on sets has considered the use of summation in a latent space to enforce permutation invariance. In particular, it has been conjectured that the dimension of this latent space may remain fixed as the cardinality of the sets under consideration increases. However, we demonstrate that the analysis leading to this conjecture requires mappings which are highly discontinuous and argue that this is only of limited practical use. Motivated by this observation, we prove that an implementation of this model via continuous mappings (as provided by e.g. neural networks or Gaussian processes) actually imposes a constraint on the dimensionality of the latent space. Practical universal function representation for set inputs can only be achieved with a latent dimension at least the size of the maximum number of input elements.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/09/2019

No Representation without Transformation

We propose to extend Latent Variable Models with a simple idea: learn to...
research
07/05/2021

Universal Approximation of Functions on Sets

Modelling functions of sets, or equivalently, permutation-invariant func...
research
12/15/2020

Learning Aggregation Functions

Learning on sets is increasingly gaining attention in the machine learni...
research
07/25/2020

Modal Uncertainty Estimation via Discrete Latent Representation

Many important problems in the real world don't have unique solutions. I...
research
10/03/2018

Deep processing of structured data

We construct a general unified framework for learning representation of ...
research
11/19/2013

Nonparametric Bayes dynamic modeling of relational data

Symmetric binary matrices representing relations among entities are comm...
research
01/18/2021

Visualizing Missing Surfaces In Colonoscopy Videos using Shared Latent Space Representations

Optical colonoscopy (OC), the most prevalent colon cancer screening tool...

Please sign up or login with your details

Forgot password? Click here to reset