DeepAI AI Chat
Log In Sign Up

The passive symmetries of machine learning

by   Soledad Villar, et al.

Any representation of data involves arbitrary investigator choices. Because those choices are external to the data-generating process, each choice leads to an exact symmetry, corresponding to the group of transformations that takes one possible representation to another. These are the passive symmetries; they include coordinate freedom, gauge symmetry and units covariance, all of which have led to important results in physics. Our goal is to understand the implications of passive symmetries for machine learning: Which passive symmetries play a role (e.g., permutation symmetry in graph neural networks)? What are dos and don'ts in machine learning practice? We assay conditions under which passive symmetries can be implemented as group equivariances. We also discuss links to causal modeling, and argue that the implementation of passive symmetries is particularly valuable when the goal of the learning problem is to generalize out of sample. While this paper is purely conceptual, we believe that it can have a significant impact on helping machine learning make the transition that took place for modern physics in the first half of the Twentieth century.


page 1

page 2

page 3

page 4


Dimensionless machine learning: Imposing exact units equivariance

Units equivariance is the exact symmetry that follows from the requireme...

Branch Identification in Passive Optical Networks using Machine Learning

A machine learning approach for improving monitoring in passive optical ...

Symmetry constrained machine learning

Symmetry, a central concept in understanding the laws of nature, has bee...

Passive Haptic Rehearsal for Accelerated Piano Skill Acquisition

Passive haptic learning (PHL) uses vibrotactile stimulation to train pia...

Minimal model of permutation symmetry in unsupervised learning

Permutation of any two hidden units yields invariant properties in typic...

Nonlinearities in Steerable SO(2)-Equivariant CNNs

Invariance under symmetry is an important problem in machine learning. O...

Passive learning of active causal strategies in agents and language models

What can be learned about causality and experimentation from passive dat...