Lorenzo Dall'Amico

Lorenzo Dall'Amico

Postdoctoral fellow

ISI foundation

Biography

I am currently a postodoctoral fellow in the group led by Prof. Ciro Cattuto at the ISI foundation in Turin, Italy. Im also an assistant professor at University of Torino, teaching a course on complex networks. My work focuses on the analysis of complex, temporal and proximity networks, with a particular emphasis on finding appropriate and interpretable representations of these high-dimensional data structures. I use methods at the crossroad of statistical physics, mathematics and computer science. My interests span from theoretical problems to data driven ones with applications to social sciences, epidemiology and human behavior modeling.

Interests

  • Graph science
  • Machine learning
  • Data for good
  • Data science
  • Statistical physics

Education

  • PhD in signal, image, speech and telecommunications, 2021

    Université Grenoble Aples

  • Master degree in Physics of complex systems, 2018

    Politecnico di Torino

  • M2 in Physics of complex systems, 2018

    Paris Sud (XI)

  • BSc in physical engineering, 2016

    Politecnico di Torino

Recent Publications

Quickly discover relevant content by filtering publications.

Resilience of mobility network to dynamic population response across COVID-19 interventions: evidences from Chile

We explore the variations of mobility across the Covid-19 waves in Chile and correlate it with several demographic indicators.

An embedding-based distance for temporal graphs

In this article we propose a definition of distance between temporal graphs.

Political context of the European vaccine debate on Twitter

We examine the relationship between the political interest of social media users and their exposure to vaccine-hesitant content on Twitter, focusing on 17 European countries using a multilingual, longitudinal dataset of tweets spanning the period before COVID, up to the vaccine roll-out.

Association of close-range contact patterns with SARS-CoV-2: a household transmission study

We studied the association between of close-range contact patterns with SARS-CoV-2 transmission. We deployed proximity sensors for two weeks to measure face-to-face interactions between household members after SARS-CoV-2 was identified in the household, in South Africa, 2020–2021.

Generalized contact matrices for epidemic modeling

In this article we explore the impact that higher resolution, generalized contact matrices have on epidemic modeling.

Efficient distributed representations beyond negative sampling

In this article we introduce a fast approximation method for the softmax normalization constants and use this result to define an efficient algorithm to create distributed representations.

Estimating household contact matrices structure from easily collectable metadata

In this article we show how to reliably estimate contact matrices from easiliy collectable metadata. We exploit high resolution proximity measurements conducted in a rural and an urban village in South Africa.

Spectral methods for graph clustering

This manuscript presents the works conducted during my PhD.

Nishimori meets Bethe: a spectral method for node classification in sparse weighted graphs

In this article we show a relation between the Bethe approximation for Ising model on random graphs and the Nishimori temperature with applications to unsupervised correlation clustering.

Community detection in sparse time-evolving graphs with a dynamical Bethe-Hessian

In this article we propose an new spectral algorithm to perform spectral clustering in sparse, dynamical graphs.

Optimal Laplacian regularization for sparse spectral community detection

In this article we provide a new interpretation on why regularization helps in sparse community detection as well as providing results on the optimal regularization to be adopted.

A unified framework for spectral clustering in sparse graphs

In this article we show how the benchmark spectral clustering techniques can all be explained under the same, elegant framework. We further provide a highly performing algorithm for community detection.

Revisiting the Bethe-Hessian: Improved Community Detection in Sparse Heterogeneous Graphs

In this article we propose an improved regularization of the Bethe-Hessian matrix to perform spectral clustering in sparse graphs.

Community detection in sparse realistic graphs: improving the Bethe-Hessian

This article proposes the study of the Bethe-Hessian matrix for community reconstruction applied on networks with arbitrary degree distribution.

How does latent liquidity get revealed in the limit order book?

In this article we discuss and compare to real data a theoretical model describing the densities profile of actions in the limit order book

A mechanism for the latent liquidity revealing into the limit order book

In this manuscript we propose a mean field microscopic model to describe the density of the orders placed in the limit order book.

Contact