Praktikum am Fachbereich Mathematik - Januar 2022
Schülerinnen und Schüler der 9. bis 12. Klasse absolvieren ihr zweiwöchiges Schulpraktikum am Fachbereich Mathematik an der TU Kaiserslautern. Vom 17. bis 28. Januar haben sie die Möglichkeit, spannende Einblicke in die Welt der Mathematik zu bekommen. Neben einem Besuch von Vorlesungen lernen sie mathematische Konzepte kennen, die ihnen in Vorträgen und Workshops von Mitarbeitern und Mitarbeiterinnen des Fachbereichs Mathematik nähergebracht werden. Außerdem arbeiten sie eigenständig an Projekten, um das neu erworbene Wissen anzuwenden.
Die Praktikumsinhalte werden vom KOMMS sowie den Arbeitsgruppen des Fachbereichs Mathematik gestaltet.
Informationen zum Praktikum am Fachbereich Mathematik können hier nachgelesen werden.
Reference
Zebang Shen, Lecturer at the Department of Computer Science, Institute for Machine Learning, ETH Zürich, Switzerland
Title: Provable Maximum Entropy Manifold Exploration via Diffusion Models
Abstract:
Exploration is critical for solving real-world decision-making problems such as scientific discovery, where the objective is to generate truly novel designs rather than mimic existing data distributions. In this work, we address the challenge of leveraging the representational power of generative models for exploration without relying on explicit uncertainty quantification. We introduce a novel framework that casts exploration as entropy maximization over the approximate data manifold implicitly defined by a pre-trained diffusion model. Then, we present a novel principle for exploration based on density estimation, a problem well-known to be challenging in practice. To overcome this issue and render this method truly scalable, we leverage a fundamental connection between the entropy of the density induced by a diffusion model and its score function. Building on this, we develop an algorithm based on mirror descent that solves the exploration problem as sequential fine-tuning of a pre-trained diffusion model. We prove its convergence to the optimal exploratory diffusion model under realistic assumptions by leveraging recent understanding of mirror flows. Finally, we empirically evaluate our approach on both synthetic and high-dimensional text-to-image diffusion, demonstrating promising results.
How to join online
You can join online via Zoom, using the following link:
https://uni-kl-de.zoom-x.de/j/69269239534?pwd=Z9UOzMpkhMjrxVhll3d49sNHFe9Fd1.1
Referent: Dr. Zebang Shen, Lecturer at the Department of Computer Science, Institute for Machine Learning, ETH Zürich, Switzerland
Zeit: 10:15 Uhr
Ort: Hybrid (Room 32-349 and via Zoom)