TGTancredi Schettini Gherardini

Tancredi Schettini Gherardini

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Tancredi Schettini Gherardini has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • A user’s guide to PINNs in geometric analysis: Lessons from the asymptotic Plateau problem

    by Tancredi Schettini Gherardini

    In this paper, we describe a physics-informed neural network (PINN) framework for the asymptotic Plateau problem: the construction of minimal discs in hyperbolic space [Formula: see text] meeting the sphere at infinity along a prescribed knot. By a conjecture of Joel Fine, signed counts of such discs recover coefficients of the HOMFLY polynomial of the knot. Two aspects of the framework are described in detail. The first one concerns how to encode the geometry in the architecture: the network is one ingredient of a composite map whose boundary behavior automatically matches the prescribed knot for every value of the learnable parameters, and which meets the sphere at infinity orthogonally (therefore satisfying the asymptotically minimal condition by construction). The loss then reduces to a single interior term, involving the tension field of the minimality condition, and no weighting of boundary against interior penalties is needed. The second aspect is the cost of evaluating such loss. We compute the value, Jacobian and Hessian of the model by propagating second-order jets forward through the network in closed form, in place of nested reverse-mode automatic differentiation, and we compile the resulting computational graph once instead of rebuilding it at every optimization step. On identical hardware and in double precision, these two changes reduce the cost of a training step by a factor of between forty and fifty. We hope these methodological discussions can be useful for researchers in differential geometry and geometric analysis who wish to deploy PINNs on problems of their own.

  • Open Access

    AInstein: numerical Einstein metrics via machine learning

    by Edward Hirst, Tancredi Schettini Gherardini, Alexander G Stapleton

    A new semi-supervised machine learning package is introduced which successfully solves the Euclidean vacuum Einstein equations with a cosmological constant, without any symmetry assumptions. The model architecture contains subnetworks for each patch in the manifold-defining atlas. Each subnetwork predicts the components of a metric in its associated patch, with the relevant Einstein conditions of the form Rμν−λgμν=0 being used as independent loss components (here μ,ν=1,2,⋯,n, where n is the dimension of the Riemannian manifold, and the Einstein constant λ∈{+1,0,−1}). To ensure the consistency of the global structure of the manifold, another loss component is introduced across the patch subnetworks which enforces the coordinate transformation between the patches, g′=JTgJ, for an appropriate analytically known Jacobian J. We test our method for the case of spheres represented by a pair of patches in dimensions 2, 3, 4, and 5. In dimensions 2 and 3, the geometries have been fully classified. However, it is unknown whether a Ricci-flat metric can exist on spheres in dimensions 4 and 5. This work hints against the existence of such a metric.


  • Open Access

    Curvature of an exotic 7-sphere

    by David S. Berman, Martin Cederwall, Tancredi Schettini Gherardini

  • Open Access

    Machine Learning Toric Duality in Brane Tilings

    by Pietro Capuozzo, Tancredi Schettini Gherardini, Benjamin Suzzoni

    We apply a variety of machine learning methods to the study of Seiberg duality within 4d $\mathcal{N}=1$ quantum field theories arising on the worldvolumes of D3-branes probing toric Calabi-Yau 3-folds. Such theories admit an elegant description in terms of bipartite tessellations of the torus known as brane tilings or dimer models. An intricate network of infrared dualities interconnects the space of such theories and partitions it into universality classes, the prediction and classification of which is a problem that naturally lends itself to a machine learning investigation. In this paper, we address a preliminary set of such enquiries. We begin by training a fully connected neural network to identify classes of Seiberg dual theories realised on $\mathbb{Z}_m\times\mathbb{Z}_n$ orbifolds of the conifold and achieve $R^2=0.988$. Then, we evaluate various notions of robustness of our methods against perturbations of the space of theories under investigation, and discuss these results in terms of the nature of the neural network's learning. Finally, we employ a more sophisticated residual architecture to classify the toric phase space of the $Y^{6,0}$ theories, and to predict the individual gauged linear $σ$-model multiplicities in toric diagrams thereof. In spite of the non-trivial nature of this task, we achieve remarkably accurate results; namely, upon fixing a choice of Kasteleyn matrix representative, the regressor achieves a mean absolute error of $0.021$. We also discuss how the performance is affected by relaxing these assumptions.

  • Open Access

    Calabi-Yau four-, five-, sixfolds as Pwn hypersurfaces: Machine learning, approximation, and generation

    by Edward Hirst, Tancredi Schettini Gherardini

    Calabi-Yau fourfolds may be constructed as hypersurfaces in weighted projective spaces of complex dimension five defined via weight systems of six weights. In this work, neural networks were implemented to learn the Calabi-Yau Hodge numbers from the weight systems, where gradient saliency and symbolic regression then inspired a truncation of the Landau-Ginzburg model formula for the Hodge numbers of any dimensional Calabi-Yau constructed in this way. The approximation always provides a tight lower bound, is shown to be dramatically quicker to compute (with computation times reduced by up to 4 orders of magnitude), and gives remarkably accurate results for systems with large weights. Additionally, complementary datasets of weight systems satisfying the necessary but insufficient conditions for transversality were constructed, including considerations of the interior point, reflexivity, and intradivisibility properties, overall producing a classification of this weight system landscape, further confirmed with machine learning methods. Using the knowledge of this classification and the properties of the presented approximation, a novel dataset of transverse weight systems consisting of seven weights was generated for a sum of weights ≤200, producing a new database of Calabi-Yau fivefolds, with their respective topological properties computed. Furthermore, an equivalent database of candidate Calabi-Yau sixfolds was generated with approximated Hodge numbers.


  • Open Access

    Exotic Spheres' Metrics and Solutions via Kaluza-Klein Techniques

    by T. Schettini Gherardini

    By applying an inverse Kaluza-Klein procedure, we provide explicit coordinate expressions for Riemannian metrics on two homeomorphic but not diffeomorphic spheres in seven dimensions. We identify Milnor's bundles, among which ten out of the fourteen exotic seven-spheres appear (ignoring orientation), with non-principal bundles having homogeneous fibres. Then, we use the techniques in \cite{10.1063/1.525753} to obtain a general ansatz for the coordinate expression of a metric on the total space of any Milnor's bundle. The ansatz is given in terms of a metric on $S^4$, a metric on $S^3$ (which can smoothly vary throughout $S^4$), and a connection on the principal $SO(4)$-bundle over $S^4$. As a concrete example, we present explicit formulae for such metrics for the ordinary sphere and the Gromoll-Meyer exotic sphere. Then, we perform a non-abelian Kaluza-Klein reduction to gravity in seven dimensions, according to (a slightly simplified version of) the metric ansatz above. We obtain the standard four-dimensional Einstein-Yang-Mills system, for which we find solutions associated with the geometries of the ordinary sphere and of the exotic one. The two differ by the winding numbers of the instantons involved.

  • Open Access

    Constructing and Machine Learning Calabi-Yau Five-folds

    by R. Alawadhi, D. Angella, A. Leonardo, T. Schettini Gherardini

    We construct all possible complete intersection Calabi-Yau five-folds in a product of four or less complex projective spaces, with up to four constraints. We obtain $27068$ spaces, which are not related by permutations of rows and columns of the configuration matrix, and determine the Euler number for all of them. Excluding the $3909$ product manifolds among those, we calculate the cohomological data for $12433$ cases, i.e. $53.7 \%$ of the non-product spaces, obtaining $2375$ different Hodge diamonds. The dataset containing all the above information is available at https://www.dropbox.com/scl/fo/z7ii5idt6qxu36e0b8azq/h?rlkey=0qfhx3tykytduobpld510gsfy&dl=0 . The distributions of the invariants are presented, and a comparison with the lower-dimensional analogues is discussed. Supervised machine learning is performed on the cohomological data, via classifier and regressor (both fully connected and convolutional) neural networks. We find that $h^{1,1}$ can be learnt very efficiently, with very high $R^2$ score and an accuracy of $96\%$, i.e. $96 \%$ of the predictions exactly match the correct values. For $h^{1,4},h^{2,3}, η$, we also find very high $R^2$ scores, but the accuracy is lower, due to the large ranges of possible values.

  • Open Access

    Constructing and Machine Learning Calabi‐Yau Five‐Folds

    by Rashid Alawadhi, Daniele Angella, Andrea Leonardo, Tancredi Schettini Gherardini

    Motivated by their role in M‐theory, F‐theory, and S‐theory compactifications, all possible complete intersections Calabi‐Yau five‐folds in a product of four or less complex projective spaces are constructed, with up to four constraints. A total of 27 068 spaces are obtained, which are not related by permutations of rows and columns of the configuration matrix, and determine the Euler number for all of them. Excluding the 3909 product manifolds among those, the cohomological data for 12 433 cases are calculated, i.e., 53.7% of the non‐product spaces, obtaining 2375 different Hodge diamonds. The dataset containing all the above information is available here. The distributions of the invariants are presented, and a comparison with the lower‐dimensional analogues is discussed. Supervised machine learning is performed on the cohomological data, via classifier, and regressor (both fully connected and convolutional) neural networks. h1, 1 can be learnt very efficiently, with very high R2 score and an accuracy of 96% is found, i.e., 96% of the predictions exactly match the correct values. For , very high R2 scores are also found, but the accuracy is lower, due to the large ranges of possible values.


  • Open Access

    Exotic spheres’ metrics and solutions via Kaluza-Klein techniques

    by T. Schettini Gherardini

    By applying an inverse Kaluza-Klein procedure, we provide explicit coordinate expressions for Riemannian metrics on two homeomorphic but not diffeomorphic spheres in seven dimensions. We identify Milnor’s bundles, among which ten out of the fourteen exotic seven-spheres appear (ignoring orientation), with non-principal bundles having homogeneous fibres. Then, we use the techniques in [1] to obtain a general ansatz for the coordinate expression of a metric on the total space of any Milnor’s bundle. The ansatz is given in terms of a metric on S4, a metric on S3 (which can smoothly vary throughout S4), and a connection on the principal SO(4)-bundle over S4. As a concrete example, we present explicit formulae for such metrics for the ordinary sphere and the Gromoll-Meyer exotic sphere. Then, we perform a non-abelian Kaluza-Klein reduction to gravity in seven dimensions, according to (a slightly simplified version of) the metric ansatz above. We obtain the standard four-dimensional Einstein-Yang-Mills system, for which we find solutions associated with the geometries of the ordinary sphere and of the exotic one. The two differ by the winding numbers of the instantons involved.


  • Open Access

    Twisted Self-duality

    by David S. Berman, Tancredi Schettini Gherardini

    We examine a generalisation of the usual self-duality equations for Yang-Mills theory when the colour space admits a non-trivial involution. This involution allows us to construct a non-trivial twist which may be combined with the Hodge star to form a twisted self-dual curvature. We will construct a simple example of twisted self-duality for $su(2) \oplus su(2)$ gauge theory along with its explicit solutions and then dimensionally reduce from four dimensions to obtain families of non-trivial non-linear equations in lower dimensions. This twisted self-duality constraint will be shown to arise in E_7 exceptional field theory through a Scherk-Schwarz reduction and we will show how an Eguchi-Hanson gravitational instanton also obeys the twisted self-duality condition.