Event Information:

• Thu

  10

  Jul

  2025

  SC Seminar: Zebang Shen

  10:15 Hybrid (Room 32-349 and via Zoom)

  Dr. 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