Dimitri Marinelli

MSCA researcher

FinNet

About me

I am a researcher and financial data scientist: I have been awarded of the Marie Skłodowska-Curie Postdoctoral Fellowship, part of the H2020 European Commission programme, to work at the interface of data science, applied mathematics, and finance, in Munich Re. Previously, in Firamis. Before, I have been an associate researcher at the Romanian Institute for Science and Technology, where I worked on Deep Learning and Information geometry in the Machine Learning and Optimization Lab directed by Luigi Malagò, in the context of the DeepRiemann project “Riemannian Optimization Methods for Deep Learning”, funded by European structural funds.

My current research consists of studying financial risk and asset management by leveraging machine learning and quantitative analysis.

Education

  • PhD in Mathematical Physics

    Università degli Studi di Pavia, Italy

  • Master in Theoretical Physics

    Università degli Studi di Perugia, Italy

Recent Publications

Quickly discover relevant content by filtering publications.

Understanding Machine Learning for Diversified Portfolio Construction by Explainable AI

In this paper, we construct a pipeline to investigate heuristic diversification strategies in asset allocation. We use machine learning …

Explainable AI in credit risk management

The paper proposes an explainable AI model that can be used in credit risk management and, in particular, in measuring the risks that …

Parameters Estimation for the Cosmic Microwave Background with Bayesian Neural Networks

In this paper, we present the first study that compares different models of Bayesian Neural Networks (BNNs) to predict the posterior …

Thermodynamics of Quantum Phase Transitions of a Dirac Oscillator in a Homogenous Magnetic Field

The Dirac oscillator in a homogenous magnetic field exhibits a chirality phase transition at a particular (critical) value of the …

Synthetic Generation of Local Minima and Saddle Points for Neural Networks

In this work-in-progress paper, we study the landscape of the empirical loss function of a feed-forward neural network, from the …

Spin-Coupling Diagrams and Incidence Geometry: A Note on Combinatorial and Quantum-Computational Aspects

This paper continues previous work on quantum mechanical angular momentum theory and its applications. Relationships with projective …

A Practical Look at Regge Calculus

Regge calculus is the classical starting point for a bunch of different models of quantum gravity. Moreover, it is often considered a …

Single and Collective Dynamics of Discretized Geometries

This paper reports a summary of the results of the PhD thesis. It is divided into two parts. In the first part the dynamics of the …

Symmetric coupling of angular momenta, quadratic algebras and discrete polynomials

Eigenvalues and eigenfunctions of the volume operator, associated with the symmetric coupling of three SU(2) angular momentum …

Symmetric angular momentum coupling, the quantum volume operator and the 7-spin network: a computational perspective

A unified vision of the symmetric coupling of angular momenta and of the quantum mechanical volume operator is illustrated. The focus …

Contact