High-Dimensional Optimization with Diffusion Models investigates the use of diffusion-based generative models as optimization mechanisms in high-dimensional search spaces. The project explores how reverse diffusion processes can be conditioned on objective functions to iteratively generate candidate solutions that concentrate around optimal regions of complex landscapes. The work will study approaches such as score-based diffusion, masked diffusion models (for discrete structures), and constraint conditioning to bias the generative process toward high-quality solutions, with a focus on scalability, multimodal objectives, and robustness in very high-dimensional settings. The goal is to develop and evaluate diffusion-driven optimization algorithms capable of efficiently exploring complex solution spaces and competing with or complementing classical optimization techniques.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
Job Type
Full-time
Career Level
Intern
Education Level
No Education Listed
Number of Employees
1,001-5,000 employees