Equivariant Hamiltonian Flows

09/30/2019
by   Danilo Jimenez Rezende, et al.
0

This paper introduces equivariant hamiltonian flows, a method for learning expressive densities that are invariant with respect to a known Lie-algebra of local symmetry transformations while providing an equivariant representation of the data. We provide proof of principle demonstrations of how such flows can be learnt, as well as how the addition of symmetry invariance constraints can improve data efficiency and generalisation. Finally, we make connections to disentangled representation learning and show how this work relates to a recently proposed definition.

READ FULL TEXT
research
03/30/2019

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

Finding a generally accepted formal definition of a disentangled represe...
research
01/19/2023

Hamiltonian Neural Networks with Automatic Symmetry Detection

Recently, Hamiltonian neural networks (HNN) have been introduced to inco...
research
02/08/2019

Invariant-equivariant representation learning for multi-class data

Representations learnt through deep neural networks tend to be highly in...
research
12/05/2018

Towards a Definition of Disentangled Representations

How can intelligent agents solve a diverse set of tasks in a data-effici...
research
07/06/2020

SurVAE Flows: Surjections to Bridge the Gap between VAEs and Flows

Normalizing flows and variational autoencoders are powerful generative m...
research
08/30/2023

Symmetry Preservation in Hamiltonian Systems: Simulation and Learning

This work presents a general geometric framework for simulating and lear...
research
02/02/2023

Oracle-Preserving Latent Flows

We develop a deep learning methodology for the simultaneous discovery of...

Please sign up or login with your details

Forgot password? Click here to reset