Gibbs Manifolds
Gibbs manifolds are images of linear spaces of symmetric matrices under the exponential map. They arise in applications such as optimization, statistics and quantum physics, where they extend the ubiquitous role of toric geometry. The Gibbs variety is the zero locus of all polynomials that vanish on the Gibbs manifold. We compute these polynomials and show that the Gibbs variety is low-dimensional. Our theory is applied to a wide range of scenarios, including matrix pencils and quantum optimal transport. This is joint work with Dmitrii Pavlov and Simon Telen.
Praktische info:
Inschrijven?
- Voorwaarden: foundational understanding of artificial intelligence, numerical optimization, and mathematical concepts
- Prijs: free
Georganiseerd door:
Lesgever/spreker
Bernd Sturmfels
Max Planck Institute for Mathematics in Leipzig, Germany
Back to the Roots Seminar Series
The ERC research project "Back to the roots of data-driven dynamical system identification", led by Prof. Dr. Bart De Moor (KU Leuven, ESAT-STADIUS), focuses on system identification, where mathematical models are derived from observed data generated by systems such as medical monitoring, electricity consumption and industrial processes. Utilizing optimization algorithms, one seeks to identify the best model in a chosen model class. This methodology finds widespread application across thousands of use cases within the AI community. However, there is no guarantee that optimization algorithms will find the best model. Present-day optimization practices are heuristic in nature, yielding results that may not be reproducible and consequently difficult to interpret.
The main objective of the Back to the Roots project is to develop a theoretical framework that combines model classes and optimization algorithms, enabling the calculation of the optimal model within the specified model class with 100% certainty.
Gerelateerde opleidingen
Interdisciplinary School on Machine Learning and AI for Science
Interdisciplinary school - Heilbronn - ETH Zürich
Machine Learning Specialization
opleiding - online - DeepLearning.AI, Stanford Online