Embedded Files
Aim & Scope
Aim & Scope
As machine learning increasingly reshapes how models are built and decisions are made, the workshop explores how control-theoretic principles can contribute to the design, analysis, and deployment of intelligent systems, providing structure, interpretability, safety, and performance guarantees in data-driven environments.
The workshop is structured around four key themes that highlight emerging connections between control, optimization, and machine learning, including:
Interpretability and Explainability in Learning Systems, exploring how control-theoretic ideas and system identification can contribute to understanding and explaining complex machine learning models.
Bridging Theory and Practice, examining how control-theoretic principles such as feedback, robustness, and stability can help connect theoretical developments with practical implementations in modern AI-driven systems.
Guarantees for Learning-Based Decision Making, investigating how control theory can provide safety, reliability, and performance guarantees in systems that incorporate machine learning.
Applications Beyond Traditional Domains, showcasing how control-theoretic ideas can inform emerging applications such as social, biological, and financial systems.
Through these themes, the workshop offers complementary perspectives on the evolving role of systems and control theory in the era of artificial intelligence, presenting cutting-edge methodologies and illustrating their relevance for modern intelligent systems.
The workshop will conclude with a round-table discussion bringing together panelists, speakers and participants to reflect on these developments, discuss emerging research directions, and foster new collaborations.
Target audience
Target audience
The workshop is open to a broad audience, ranging from graduate students exploring potential research directions to senior researchers interested in engaging with research directions and challenges that could shape the future of control theory. Given the macro-themes of the talks, the workshop aims to attract theorists interested in the impact of control-theoretic tools on machine learning–based applications, as well as to researchers working at the boundaries between machine learning and control who seek an overview of how closed-loop reasoning and control concepts can support interpretability, safety, robustness, and to practitioners interested in emerging perspectives at the intersection of machine learning, optimization, and control with relevance to societal challenges.
The Talks
The Talks
The workshop brings together a diverse group of internationally recognized researchers from leading institutions in Europe and the United States, with a particular focus on emerging voices in the field. Their talks offer fresh perspectives on the interplay between control theory, machine learning, and optimization, highlighting new directions for the development of intelligent systems. Follow here for more details on the invited talks.
Page updated
Google Sites
Report abuse