Two Faces of Optimization:
From Offline Control to Sequential Decisions
July 8–9, 2025 · ETH Zurich, Switzerland
Optimization lies at the core of modern machine learning, underpinning both the design of algorithms and the analysis of their performance. This two-day workshop explores recent advances in the theory of optimization from two complementary perspectives. The first day focuses on stochastic approaches, including sampling algorithms, the dynamics of stochastic gradient methods, and probabilistic frameworks with connections to optimal transport. The second day turns to adaptive optimization, highlighting developments in reinforcement learning, bandits, and control, with an emphasis on methodology and fundamental limits.
Speakers
University of Tübingen
Boston University and Broad Institute of MIT and Harvard
Massachusetts Institute of Technology
University of Washington
Università degli Studi di Milano and Politecnico di Milano
Contributed Talks
- Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring – Khaled Eldowa , Università degli Studi di Milano and Politecnico di Milano
Schedule
The agenda will be announced soon.
Attendance
Held at the ETH AI Center, the workshop will be a small gathering accommodating a limited number of attendees. Details of attendance and poster presentation will be announced soon. In the meantime, you may contact pkassraie@ethz.ch with your inquiries.