Learning for Decision and Control through the Scenario Approach

Date: December 9, 2025   |   Location: IEEE CDC 2025, Rio de Janeiro, Brazil

Room: To be decided   |   Time: Full day

Workshop Description

This one-day workshop offers a forum for discussion on issues, challenges, and opportunities of contemporary interest regarding the wise usage of data in science and engineering. The problem is seen under the lens of the so-called scenario approach, a well-established methodology for data-driven decision-making, which has evolved over the past two decades into a comprehensive framework for using data in control design, estimation, prediction, and machine learning among others engineering applications.

Scenario Approach Diagram

In many decision-making problems, decisions are made so as to optimize performance while satisfying constraints in the presence of uncertainty. Often, the only information available about uncertainty comes from a finite set of observations, commonly referred to as scenarios. A fundamental question then arises:

Can decisions based on such limited data be trusted when facing new, unseen instances of uncertainty?

Scenario theory provides a rigorous framework to address this challenge. By offering formal risk guarantees, it turns widely used data-driven heuristics into statistically sound methods under minimal assumptions on the data-generating process.

This workshop offers an introduction to the scenario approach to learning-based decision and control for researchers new to the subject. Designed to strike a balance between foundational results and practical applications, the workshop features leading experts sharing state-of-the-art theory and algorithms related to:

and with application to:

The workshop targets graduate students, control engineers, and researchers in systems & control, machine learning, and decision-making.

Key Goals

Organizers & Speakers

Marco C. Campi

Marco Campi (organizer)
University of Brescia

Algo Carè

Algo Carè (organizer)
University of Brescia

Simone Garatti

Simone Garatti (organizer)
Politecnico di Milano

Maria Prandini

Maria Prandini
Politecnico di Milano

Licio Romao

Licio Romao
Technical University of Denmark

Schedule

09:00 - 09:15: Introduction and motivation

09:15 - 10:30: Simone Garatti - The Scenario Approach in the dawn of sample-based and data-driven design methods

10:30 - 11:00: Coffee break

11:00 - 12:15: Maria Prandini - Optimal constrained control of stochastic linear systems operating in stationary conditions

12:15 - 13:30: Lunch break

13:30 - 14:45: Marco Campi - Scenario Optimization: the boon of direct design and the marriage between risk and complexity

14:45 - 16:00: Algo Carè - Guaranteed supervised classification for medical applications

16:00 - 16:30: Coffee break

16:30 - 17:45: Licio Romao - A tight PAC bound on the sampling-and-discarding approach to scenario optimization and its connection to dynamical system abstraction

Registration

To register, please visit the IEEE CDC 2025 website.

Contact

For additional information, contact: algo.care@unibs.it