Identifying Physical Law of Hamiltonian Systems via Meta-Learning

• URL: http://arxiv.org/abs/2102.11544v1
• Date: Tue, 23 Feb 2021 08:16:13 GMT
• Title: Identifying Physical Law of Hamiltonian Systems via Meta-Learning
• Authors: Seungjun Lee, Haesang Yang, Woojae Seong
• Abstract summary: Hamiltonian mechanics is an effective tool to represent many physical processes. We show that a well meta-trained learner can identify the shared representation of the Hamiltonian.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hamiltonian mechanics is an effective tool to represent many physical processes with concise yet well-generalized mathematical expressions. A well-modeled Hamiltonian makes it easy for researchers to analyze and forecast many related phenomena that are governed by the same physical law. However, in general, identifying a functional or shared expression of the Hamiltonian is very difficult. It requires carefully designed experiments and the researcher's insight that comes from years of experience. We propose that meta-learning algorithms can be potentially powerful data-driven tools for identifying the physical law governing Hamiltonian systems without any mathematical assumptions on the representation, but with observations from a set of systems governed by the same physical law. We show that a well meta-trained learner can identify the shared representation of the Hamiltonian by evaluating our method on several types of physical systems with various experimental settings.

Related papers

• Quantum Simulation of Nonlinear Dynamical Systems Using Repeated Measurement [42.896772730859645]
  We present a quantum algorithm based on repeated measurement to solve initial-value problems for nonlinear ordinary differential equations. We apply this approach to the classic logistic and Lorenz systems in both integrable and chaotic regimes.
  arXiv  Detail & Related papers  (2024-10-04T18:06:12Z)
• Learning Generalized Hamiltonians using fully Symplectic Mappings [0.32985979395737786]
  Hamiltonian systems have the important property of being conservative, that is, energy is conserved throughout the evolution. In particular Hamiltonian Neural Networks have emerged as a mechanism to incorporate structural inductive bias into the NN model. We show that symplectic schemes are robust to noise and provide a good approximation of the system Hamiltonian when the state variables are sampled from a noisy observation.
  arXiv  Detail & Related papers  (2024-09-17T12:45:49Z)
• Physics-Informed Neural Networks for Dynamic Process Operations with Limited Physical Knowledge and Data [38.39977540117143]
  In chemical engineering, process data are expensive to acquire, and complex phenomena are difficult to fully model. In particular, we focus on estimating states for which neither direct data nor observational equations are available. We show that PINNs are capable of modeling processes when relatively few experimental data and only partially known mechanistic descriptions are available.
  arXiv  Detail & Related papers  (2024-06-03T16:58:17Z)
• Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms [48.869199703062606]
  A fundamental problem in quantum many-body physics is that of finding ground states of local Hamiltonians. We introduce two approaches that achieve a constant sample complexity, independent of system size $n$, for learning ground state properties.
  arXiv  Detail & Related papers  (2024-05-28T18:00:32Z)
• Quantum-probabilistic Hamiltonian learning for generative modelling & anomaly detection [0.0]
  This study investigates the possibility of learning and utilising a system's Hamiltonian for data analysis techniques. We employ the method of Quantum Hamiltonian-based models for the generative modelling of simulated Large Hadron Collider data. In a further step, we use the learned Hamiltonian for anomaly detection, showing that different sample types can form distinct dynamical behaviours.
  arXiv  Detail & Related papers  (2022-11-07T19:00:02Z)
• Scalably learning quantum many-body Hamiltonians from dynamical data [1.702884126441962]
  We introduce a highly scalable, data-driven approach to learning families of interacting many-body Hamiltonians from dynamical data. Our approach is highly practical, experimentally friendly, and intrinsically scalable to allow for system sizes of above 100 spins.
  arXiv  Detail & Related papers  (2022-09-28T18:00:57Z)
• Learning Neural Hamiltonian Dynamics: A Methodological Overview [109.40968389896639]
  Hamiltonian dynamics endows neural networks with accurate long-term prediction, interpretability, and data-efficient learning. We systematically survey recently proposed Hamiltonian neural network models, with a special emphasis on methodologies.
  arXiv  Detail & Related papers  (2022-02-28T22:54:39Z)
• Robust and Efficient Hamiltonian Learning [2.121963121603413]
  We present a robust and efficient Hamiltonian learning method that circumvents limitations based on mild assumptions. The proposed method can efficiently learn any Hamiltonian that is sparse on the Pauli basis using only short-time dynamics and local operations. We numerically test the scaling and the estimation accuracy of the method for transverse field Ising Hamiltonian with random interaction strengths and molecular Hamiltonians.
  arXiv  Detail & Related papers  (2022-01-01T13:48:15Z)
• A Differentiable Newton Euler Algorithm for Multi-body Model Learning [34.558299591341]
  We motivate a computation graph architecture that embodies the Newton Euler equations. We describe the used virtual parameters that enable unconstrained physical plausible dynamics. We show that the kinematic parameters, required by previous white-box system identification methods, can be accurately inferred from data.
  arXiv  Detail & Related papers  (2020-10-19T19:30:33Z)
• Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting [34.61959169976758]
  APHYNITY is a principled approach for augmenting incomplete physical dynamics described by differential equations with deep data-driven models. It consists in decomposing the dynamics into two components: a physical component accounting for the dynamics for which we have some prior knowledge, and a data-driven component accounting for errors of the physical model.
  arXiv  Detail & Related papers  (2020-10-09T09:31:03Z)
• Learning models of quantum systems from experiments [0.2740360306052669]
  Hamiltonian models underpin the study and analysis of physical and chemical processes throughout science and industry. We propose and demonstrate an approach to retrieving a Hamiltonian model from experiments, using unsupervised machine learning.
  arXiv  Detail & Related papers  (2020-02-14T18:37:50Z)

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.