Noether's razor: Learning Conserved Quantities

• URL: http://arxiv.org/abs/2410.08087v1
• Date: Thu, 10 Oct 2024 16:29:49 GMT
• Title: Noether's razor: Learning Conserved Quantities
• Authors: Tycho F. A. van der Ouderaa, Mark van der Wilk, Pim de Haan,
• Abstract summary: 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.
• Score: 16.81984465529089
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Symmetries have proven useful in machine learning models, improving generalisation and overall performance. At the same time, recent advancements in learning dynamical systems rely on modelling the underlying Hamiltonian to guarantee the conservation of energy. These approaches can be connected via a seminal result in mathematical physics: Noether's theorem, which states that symmetries in a dynamical system correspond to conserved quantities. This work uses Noether's theorem to parameterise symmetries as learnable conserved quantities. We then allow conserved quantities and associated symmetries to be learned directly from train data through approximate Bayesian model selection, jointly with the regular training procedure. As training objective, we derive a variational lower bound to the marginal likelihood. The objective automatically embodies an Occam's Razor effect that avoids collapse of conservation laws to the trivial constant, without the need to manually add and tune additional regularisers. We demonstrate a proof-of-principle on $n$-harmonic oscillators and $n$-body systems. We find that our method correctly identifies the correct conserved quantities and U($n$) and SE($n$) symmetry groups, improving overall performance and predictive accuracy on test data.

Related papers

• Approximate Equivariance in Reinforcement Learning [35.04248486334824]
  Equivariant neural networks have shown great success in reinforcement learning. In many problems, only approximate symmetry is present, which makes imposing exact symmetry inappropriate. We develop approximately equivariant algorithms in reinforcement learning.
  arXiv  Detail & Related papers  (2024-11-06T19:44:46Z)
• 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)
• Tempered Calculus for ML: Application to Hyperbolic Model Embedding [70.61101116794549]
  Most mathematical distortions used in ML are fundamentally integral in nature. In this paper, we unveil a grounded theory and tools which can help improve these distortions to better cope with ML requirements. We show how to apply it to a problem that has recently gained traction in ML: hyperbolic embeddings with a "cheap" and accurate encoding along the hyperbolic vsean scale.
  arXiv  Detail & Related papers  (2024-02-06T17:21:06Z)
• 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)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Third quantization of open quantum systems: new dissipative symmetries and connections to phase-space and Keldysh field theory formulations [77.34726150561087]
  We reformulate the technique of third quantization in a way that explicitly connects all three methods. We first show that our formulation reveals a fundamental dissipative symmetry present in all quadratic bosonic or fermionic Lindbladians. For bosons, we then show that the Wigner function and the characteristic function can be thought of as ''wavefunctions'' of the density matrix.
  arXiv  Detail & Related papers  (2023-02-27T18:56:40Z)
• Generative Adversarial Symmetry Discovery [19.098785309131458]
  LieGAN represents symmetry as interpretable Lie algebra basis and can discover various symmetries. The learned symmetry can also be readily used in several existing equivariant neural networks to improve accuracy and generalization in prediction.
  arXiv  Detail & Related papers  (2023-02-01T04:28:36Z)
• Towards fully covariant machine learning [0.0]
  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.
  arXiv  Detail & Related papers  (2023-01-31T16:01:12Z)
• 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-optimal-control-inspired ansatz for variational quantum algorithms [105.54048699217668]
  A central component of variational quantum algorithms (VQA) is the state-preparation circuit, also known as ansatz or variational form. Here, we show that this approach is not always advantageous by introducing ans"atze that incorporate symmetry-breaking unitaries. This work constitutes a first step towards the development of a more general class of symmetry-breaking ans"atze with applications to physics and chemistry problems.
  arXiv  Detail & Related papers  (2020-08-03T18:00:05Z)

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.