Two Faces of Optimization:
From Offline Control to Sequential Decisions

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

Claire Vernade

University of Tübingen

Aldo Pacchiano

Boston University and Broad Institute of MIT and Harvard

Ayush Sekhari

Massachusetts Institute of Technology

Aditi Krishnapriyan

University of California, Berkeley

Kevin Jamieson

University of Washington

Nicolo Cesa-Bianchi

Università degli Studi di Milano and Politecnico di Milano

Short Talks

• Confidence Estimation via Sequential Likelihood Mixing – Johannes Kirschner, The Swiss Data Science Center
• Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring – Khaled Eldowa , Università degli Studi di Milano and Politecnico di Milano

Attend and Present

Held at the ETH AI Center, the workshop will be a small gathering accommodating a limited number of attendees. To help us plan, please submit your attendance request using the following form:

Register to Attend

To present a recent work as a poster, you can submit an abstract or a paper and will receive a decision back within a week of the submission. The list of accepted posters will be added to the website, and printing dimensions will be soon specified.

Submit a Poster

Schedule

Organizers