Jointly hosted by CAM, ORIE, and CDSES, Mengi Wang will give a Data Science Distinguished Lecture as follows:

Title:  Capitalizing on Generative AI: Guided Diffusion Models Towards Generative Optimization

Diffusion models represent a significant breakthrough in generative AI, operating by progressively transforming random noise distributions into structured outputs, with adaptability for specific tasks through training-free guidance or selfplay fine-tuning. In this presentation, we delve into the statistical and optimization aspects of diffusion models and establish their connection to theoretical optimization frameworks. We explore how unconditioned diffusion models efficiently capture complex high-dimensional data, particularly when low-dimensional structures are present. Further, we leverage our understanding of diffusion models to introduce a pioneering optimization method termed "generative optimization." Here, we harness diffusion models as data-driven solution generators to maximize any user-specified reward function. We introduce gradient-based guidance to guide the sampling process of a diffusion model while preserving the learnt low-dim data structure.  We show that adapting a pre-trained diffusion model with guidance is essentially equivalent to solving a regularized optimization problem. Additionally, we propose to find global optimizers through iterative self-play and fine-tuning the score network using new samples together with gradient guidance. This process mimics a first-order optimization iteration, for which we established convergence to the global optimum while maintaining intrinsic structures within the training data. Finally, we demonstrated the applications of these methods in life science, engineering designs, and video generation.

Bio: Mengdi Wang is Co-Director of Princeton AI for Accelerated Invention, and associate professor at the Department of Electrical and Computer Engineering and the Center for Statistics and Machine Learning at Princeton University. She is also affiliated with the Department of Computer Science, Omenn-Darling Bioengineering Institute, and Princeton Language+Intelligence. She was a visiting research scientist at Google DeepMind, IAS and Simons Institute on Theoretical Computer Science. Her research focuses on machine learning, reinforcement learning, generative AI, large language models, and AI for science.

Mengdi received her PhD in Electrical Engineering and Computer Science from Massachusetts Institute of Technology in 2013, where she was affiliated with the Laboratory for Information and Decision Systems and advised by Dimitri P. Bertsekas. Before that, she got her bachelor degree from the Department of Automation, Tsinghua University. Mengdi received the Young Researcher Prize in Continuous Optimization of the Mathematical Optimization Society in 2016 (awarded once every three years), the Princeton SEAS Innovation Award in 2016, the NSF Career Award in 2017, the Google Faculty Award in 2017,  and the MIT Tech Review 35-Under-35 Innovation Award (China region) in 2018, WAIC YunFan Award 2022, American Automatic Control Council’s Donald Eckman Award 2024 for “extraordinary contributions to the intersection of control, dynamical systems, machine learning and information theory”. She serves as a Program Chair for ICLR 2023 and Senior AC for Neurips, ICML, COLT, associate editor for Harvard Data Science Review, Operations Research. Research supported by NSF, AFOSR, NIH, ONR, Google, Microsoft C3.ai, FinUP, RVAC Medicines, MURI, GenMab.