Towards fully covariant machine learning

• URL: http://arxiv.org/abs/2301.13724v2
• Date: Wed, 28 Jun 2023 13:02:31 GMT
• Title: Towards fully covariant machine learning
• Authors: Soledad Villar (JHU), David W. Hogg (NYU, MPIA, Flatiron), Weichi Yao (NYU), George A. Kevrekidis (JHU, LANL), Bernhard Sch\"olkopf (MPI-IS)
• Abstract summary: In machine learning, the most visible passive symmetry is the relabeling or permutation symmetry of graphs. We discuss dos and don'ts for machine learning practice if passive symmetries are to be respected.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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. In machine learning, the most visible passive symmetry is the relabeling or permutation symmetry of graphs. Our goal is to understand the implications for machine learning of the many passive symmetries in play. We discuss dos and don'ts for machine learning practice if passive symmetries are to be respected. We 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. This paper is conceptual: It translates among the languages of physics, mathematics, and machine-learning. We believe that consideration and implementation of passive symmetries might help machine learning in the same ways that it transformed physics in the twentieth century.

Related papers

• Learning Infinitesimal Generators of Continuous Symmetries from Data [15.42275880523356]
  We propose a novel symmetry learning algorithm based on transformations defined with one- parameter groups. Our method is built upon minimal inductive biases, encompassing not only commonly utilized symmetries rooted in Lie groups but also extending to symmetries derived from nonlinear generators.
  arXiv  Detail & Related papers  (2024-10-29T08:28:23Z)
• Noether's razor: Learning Conserved Quantities [16.81984465529089]
  We parameterise symmetries as learnable conserved quantities. We then allow conserved quantities and associated symmetries to be learned directly from train data. We find that our method correctly identifies the correct conserved quantities and U($n$) and SE($n$) symmetry groups.
  arXiv  Detail & Related papers  (2024-10-10T16:29:49Z)
• A Unified Framework to Enforce, Discover, and Promote Symmetry in Machine Learning [5.1105250336911405]
  We provide a unifying theoretical and methodological framework for incorporating symmetry into machine learning models. We show that enforcing and discovering symmetry are linear-algebraic tasks that are dual with respect to the bilinear structure of the Lie derivative. We propose a novel way to promote symmetry by introducing a class of convex regularization functions based on the Lie derivative and nuclear norm relaxation.
  arXiv  Detail & Related papers  (2023-11-01T01:19:54Z)
• Learning Layer-wise Equivariances Automatically using Gradients [66.81218780702125]
  Convolutions encode equivariance symmetries into neural networks leading to better generalisation performance. symmetries provide fixed hard constraints on the functions a network can represent, need to be specified in advance, and can not be adapted. Our goal is to allow flexible symmetry constraints that can automatically be learned from data using gradients.
  arXiv  Detail & Related papers  (2023-10-09T20:22:43Z)
• Symmetry Induces Structure and Constraint of Learning [0.0]
  We unveil the importance of the loss function symmetries in affecting, if not deciding, the learning behavior of machine learning models. Common instances of mirror symmetries in deep learning include rescaling, rotation, and permutation symmetry. We show that the theoretical framework can explain intriguing phenomena, such as the loss of plasticity and various collapse phenomena in neural networks.
  arXiv  Detail & Related papers  (2023-09-29T02:21:31Z)
• Deep Learning Symmetries and Their Lie Groups, Algebras, and Subalgebras from First Principles [55.41644538483948]
  We design a deep-learning algorithm for the discovery and identification of the continuous group of symmetries present in a labeled dataset. We use fully connected neural networks to model the transformations symmetry and the corresponding generators. Our study also opens the door for using a machine learning approach in the mathematical study of Lie groups and their properties.
  arXiv  Detail & Related papers  (2023-01-13T16:25:25Z)
• Quantum Mechanics as a Theory of Incompatible Symmetries [77.34726150561087]
  We show how classical probability theory can be extended to include any system with incompatible variables. We show that any probabilistic system (classical or quantal) that possesses incompatible variables will show not only uncertainty, but also interference in its probability patterns.
  arXiv  Detail & Related papers  (2022-05-31T16:04:59Z)
• Dimensionless machine learning: Imposing exact units equivariance [7.9926585627926166]
  We provide a two stage learning procedure for units-equivariant machine learning. We first construct a dimensionless version of its inputs using classic results from dimensional analysis. We then perform inference in the dimensionless space.
  arXiv  Detail & Related papers  (2022-04-02T15:46:20Z)
• On the Importance of Asymmetry for Siamese Representation Learning [53.86929387179092]
  Siamese networks are conceptually symmetric with two parallel encoders. We study the importance of asymmetry by explicitly distinguishing the two encoders within the network. We find the improvements from asymmetric designs generalize well to longer training schedules, multiple other frameworks and newer backbones.
  arXiv  Detail & Related papers  (2022-04-01T17:57:24Z)
• Symmetry Group Equivariant Architectures for Physics [52.784926970374556]
  In the domain of machine learning, an awareness of symmetries has driven impressive performance breakthroughs. We argue that both the physics community and the broader machine learning community have much to understand.
  arXiv  Detail & Related papers  (2022-03-11T18:27:04Z)
• Meta-Learning Symmetries by Reparameterization [63.85144439337671]
  We present a method for learning and encoding equivariances into networks by learning corresponding parameter sharing patterns from data. Our experiments suggest that it can automatically learn to encode equivariances to common transformations used in image processing tasks.
  arXiv  Detail & Related papers  (2020-07-06T17:59:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.