Alberto Marchesi

PhD student in computer science

Hello!I'm Alberto Marchesi. I'm a third-year Ph.D. student in Computer Science at Politecnico di Milano advised by Prof. Nicola Gatti. My main research is focused on Artificial Intelligence, specifically on Algorithmic Game Theory, which combines AI techniques with economic paradigms to build artificial agents capable of strategic reasoning in conflicting interactions. My main focus is on leadership games models, which have been applied to solve many real-world problems, for example in security. I'm also interested in algorithms design, computational complexity, optimization, and machine learning.

download cv

Latest publications:

Leadership in Congestion Games: Multiple User Classes and Non-Singleton Actions.
Marchesi A., Castiglioni M., Gatti N.
To appear in the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China

Be a Leader or Become a Follower: The Strategy to Commit to with Multiple Leaders.
Castiglioni M., Marchesi A., Gatti N.
To appear in the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China

Education.

  • 2011-2014

    B.Sc. in Computer Science and Engineering, Politecnico di Milano, Italy

    Mark: 110/110 with honors.

  • 2014-2016

    M.Sc. in Computer Science and Engineering, Politecnico di Milano, Italy

    Mark: 110/110 with honors.
    Thesis: Methods for finding Leader-Follower equilibria with multiple followers.
    Advisor: Prof. Nicola Gatti.
    Co-advisors: Prof. Nicola Basilico, Prof. Stefano Coniglio.

  • 2016-2019

    Ph.D. in Information Technology, Computer Science and Engineering, Politecnico di Milano, Italy

    Topic: Leadership Games: from theory to algorithms.
    Advisor: Prof. Nicola Gatti.

Research.

Artificial Intelligence

I study how to build artificial agents capable of strategic reasoning, enabling them to make autonomous decisions while interacting with other agents and humans.

I study how to build artificial agents capable of strategic reasoning, enabling them to make autonomous decisions while interacting with other agents and humans.

Algorithmic Game Theory

I study how to mix economic paradigms and computer science in order to build new AI solutions for solving problems in several fields, from security to advertising.

I study how to mix economic paradigms and computer science in order to build new AI solutions for solving problems in several fields, from security to advertising.

Algorithms Design

I'm interested in the design of new algorithmic techniques that enables us to solve challenging problems efficiently.

I'm interested in the design of new algorithmic techniques that enables us to solve challenging problems efficiently.

Computational Complexity

I study the tractability of computational problems in order to understand which are simple and which instead are inherently complex.

I study the tractability of computational problems in order to understand which are simple and which instead are inherently complex.

My main research focuses on AI and algorithmic game theory, but I'm also really interested in algorithms, complexity, optimization, and machine learning.

Optimization

I study how to formulate real-world problems in the optimization framework and I develop new methods to find good quality solutions efficiently.

I study how to formulate real-world problems in the optimization framework and I develop new methods to find good quality solutions efficiently.

Publications.

C9

Be a Leader or Become a Follower: The Strategy to Commit to with Multiple Leaders

Castiglioni M., Marchesi A., Gatti N.

To appear in the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China

Read the article
C8

Leadership in Congestion Games: Multiple User Classes and Non-Singleton Actions

Marchesi A., Castiglioni M., Gatti N.

To appear in the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China

Read the article
C7

Quasi-Perfect Stackelberg Equilibrium

Marchesi A., Farina G., Kroer C., Gatti N., Sandholm T.

The 33rd AAAI Conference on Artificial Intelligence, AAAI 2019, Honolulu, USA

Read the article
C6

Trembling-Hand Perfection in Extensive-Form Games with Commitment

Farina G., Marchesi A., Kroer C., Gatti N., Sandholm T.

The 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden

Read the article
C5

Leadership in Singleton Congestion Games

Marchesi A., Coniglio S., Gatti N.

The 27th International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden

Read the article
C4

Computing the Strategy to Commit to in Polymatrix Games

De Nittis G., Marchesi A., Gatti N.

The 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, New Orleans, USA

Read the article
C3

Pessimistic Leader-Follower Equilibria with Multiple Followers

Coniglio S., Gatti N., Marchesi A.

The 26th International Joint Conference on Artificial Intelligence, IJCAI 2017: 171-177, Melbourne, Australia

Read the article
C2

On the Complexity of Nash Equilibrium Reoptimization

Celli A., Marchesi A., Gatti N.

The 33rd Conference on Uncertainty in Artificial Intelligence, UAI 2017: 292-301, Sydney, Australia

Read the article
C1

Bilevel Programming Approaches to the Computation of Optimistic and Pessimistic Single-Leader-Multi-Follower Equilibria

Basilico N., Coniglio S., Gatti N., Marchesi A.

The 16th International Symposium on Experimental Algorithms, SEA 2017: 31:1-31:14, London, UK

Read the article

Teaching.

Contact.

alberto.marchesi@polimi.it +39-02-2399-9685
  • Office 20, First floor, Building 21
  • Via Golgi 39, 20133, Milan
  • Dipartimento di Elettronica, Informazione e Bioingegneria
  • Politecnico di Milano