arXiv:2010.00054 · Physical Review Research

Adding machine learning within Hamiltonians: Renormalization group transformations, symmetry breaking and restoration

Dimitrios Bachtis, Gert Aarts A, Biagio Lucini A

Published Feb 10, 2021• 13 citations

Abstract

We present a physical interpretation of machine learning functions, opening up the possibility to control properties of statistical systems via the inclusion of these functions in Hamiltonians.In particular, we include the predictive function of a neural network, designed for phase classification, as a conjugate variable coupled to an external field within the Hamiltonian of a system.Results in the two-dimensional Ising model evidence that the field can induce an order-disorder phase transition by breaking or restoring the symmetry, in contrast with the field of the conventional order parameter which causes explicit symmetry breaking.The critical behavior is then studied by proposing a Hamiltonian-agnostic reweighting approach and forming a renormalization group mapping on quantities derived from the neural network.Accurate estimates of the critical point and of the critical exponents related to the operators that govern the divergence of the correlation length are provided.We conclude by discussing how the method provides an essential step toward bridging machine learning and physics.

DOI: 10.1103/physrevresearch.3.013134

Related papers

Interpreting machine learning functions as physical observables

Gert Aarts A, Dimitrios Bachtis, Biagio Lucini A

We propose to interpret machine learning functions as physical observables, opening up the possibility to apply “standard” statistical-mechanical methods to outputs from neural networks. This includes histogram reweighting and finite-size scaling, to analyse phase transitions quantitatively. In addition we incorporate predictive functions as conjugate variables coupled to an external field within the Hamiltonian of a system, allowing to induce order-disorder phase transitions in a novel manner. A noteworthy feature of this approach is that no knowledge of the symmetries in the Hamiltonian is required.

arXiv:2109.08497International Symposium on Lattice Field Theory (LATTICE)May 16, 20223 citations

Machine learning renormalization group for statistical physics

Wanda Hou, Yi‐Zhuang You

Abstract We develop a machine-learning renormalization group (MLRG) algorithm to explore and analyze many-body lattice models in statistical physics. Using the representation learning capability of generative modeling, MLRG automatically learns the optimal renormalization group (RG) transformations from self-generated spin configurations and formulates RG equations without human supervision. The algorithm does not focus on simulating any particular lattice model but broadly explores all possible models compatible with the internal and lattice symmetries given the on-site symmetry representation. It can uncover the RG monotone that governs the RG flow, assuming a strong form of the c-theorem. This enables several downstream tasks, including unsupervised classification of phases, automatic location of phase transitions or critical points, controlled estimation of critical exponents, and operator scaling dimensions. We demonstrate the MLRG method in two-dimensional lattice models with Ising symmetry and show that the algorithm correctly identifies and characterizes the Ising criticality.

arXiv:2306.11054Machine Learning Science and TechnologyOct 6, 20238 citations

Mapping distinct phase transitions to a neural network

Dimitrios Bachtis, Gert Aarts A, Biagio Lucini A

We demonstrate, by means of a convolutional neural network, that the features learned in the two-dimensional Ising model are sufficiently universal to predict the structure of symmetry-breaking phase transitions in considered systems irrespective of the universality class, order, and the presence of discrete or continuous degrees of freedom. No prior knowledge about the existence of a phase transition is required in the target system and its entire parameter space can be scanned with multiple histogram reweighting to discover one. We establish our approach in q-state Potts models and perform a calculation for the critical coupling and the critical exponents of the ϕ^{4} scalar field theory using quantities derived from the neural network implementation. We view the machine learning algorithm as a mapping that associates each configuration across different systems to its corresponding phase and elaborate on implications for the discovery of unknown phase transitions.

arXiv:2007.00355Physical review. ENov 16, 202041 citations

Quantum field-theoretic machine learning and the renormalization group

Dimitrios Bachtis

Within the past decade, machine learning algorithms have been proposed as a po-tential solution to a variety of research problems which emerge within physics. As this cross-fertilization matures, one is able to investigate if the eﬃciency of machine learning algorithms can be increased by interpreting them physically and if there exist fundamental connections that can be established between the two research ﬁelds. In this thesis, we pursue research directions intimately related to the above questions.First, we investigate the practical implications of interpreting machine learning functions as statistical-mechanical observables. Through this perspective, we explore if we can extend the classiﬁcation capabilities of machine learning algorithms and if we are able to include neural networks within Hamiltonians to induce phase transitions in systems. A related direction concerns the use of machine learning to construct inverse renormalization group transformations to arbitrarily increase the size of a system. These techniques are then utilized to study the inﬁnite volume limit of discrete spin systems and of quantum ﬁeld theories, in order to investigate if machine learning is a powerful tool to study phase transitions.In another research direction we explore the derivation of machine learning algo-rithms from quantum ﬁeld theories. We investigate if the φ4 scalar ﬁeld theory satisﬁes the Hammersley-Cliﬀord theorem and if it can be recast as a Markov random ﬁeld. We then explore if φ4 neural networks can be derived that generalize a certain class of standard neural network architectures, and we present relevant numerical appli-cations. Finally, we discuss how this research direction opens up the opportunity to investigate machine learning within quantum ﬁeld theory and how it solidiﬁes a rig-orous connection between the research ﬁelds of machine learning, probability theory, statistical mechanics, lattice and constructive quantum ﬁeld theory.

Jan 1, 20220 citations

Machine Learning as a universal tool for quantitative investigations of phase transitions

Cinzia Giannetti, Biagio Lucini A, Davide Vadacchino

The problem of identifying the phase of a given system for a certain value of the temperature can be reformulated as a classification problem in Machine Learning. Taking as a prototype the Ising model and using the Support Vector Machine as a tool to classify Monte Carlo generated configurations, we show that the critical region of the system can be clearly identified and the symmetry that drives the transition can be reconstructed from the performance of the learning process. The role of the discrete symmetry of the system in obtaining this result is discussed. A finite size analysis of the learned Support Vector Machine decision function allows us to determine the critical temperature and critical exponents with a precision that is comparable to that of the most efficient numerical approaches relying on a known Hamiltonian description of the system. For the determination of the critical temperature and of the critical exponent connected with the divergence of the correlation length, other than the availability of a range of temperatures having information on both phases, the method we propose does not rest on any physical input on the system, and in particular is agnostic to its Hamiltonian, its symmetry properties and its order parameter. Hence, our investigation provides a first significant step in the direction of devising robust tools for quantitative analyses of phase transitions in cases in which an order parameter is not known.

arXiv:1812.06726Nuclear Physics BMay 16, 201951 citations

Extending machine learning classification capabilities with histogram reweighting

Dimitrios Bachtis, Gert Aarts A, Biagio Lucini A

We propose the use of Monte Carlo histogram reweighting to extrapolate predictions of machine learning methods. In our approach, we treat the output from a convolutional neural network as an observable in a statistical system, enabling its extrapolation over continuous ranges in parameter space. We demonstrate our proposal using the phase transition in the two-dimensional Ising model. By interpreting the output of the neural network as an order parameter, we explore connections with known observables in the system and investigate its scaling behavior. A finite-size scaling analysis is conducted based on quantities derived from the neural network that yields accurate estimates for the critical exponents and the critical temperature. The method improves the prospects of acquiring precision measurements from machine learning in physical systems without an order parameter and those where direct sampling in regions of parameter space might not be possible.

arXiv:2004.14341Physical review. ESep 9, 202033 citations