تقرير
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
| العنوان: | Implicit Diffusion: Efficient Optimization through Stochastic Sampling |
|---|---|
| المؤلفون: | Marion, Pierre, Korba, Anna, Bartlett, Peter, Blondel, Mathieu, De Bortoli, Valentin, Doucet, Arnaud, Llinares-López, Felipe, Paquette, Courtney, Berthet, Quentin |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Machine Learning |
| الوصف: | We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions. Doing so allows us to modify the outcome distribution of sampling processes by optimizing over their parameters. We introduce a general framework for first-order optimization of these processes, that performs jointly, in a single loop, optimization and sampling steps. This approach is inspired by recent advances in bilevel optimization and automatic implicit differentiation, leveraging the point of view of sampling as optimization over the space of probability distributions. We provide theoretical guarantees on the performance of our method, as well as experimental results demonstrating its effectiveness. We apply it to training energy-based models and finetuning denoising diffusions. Comment: 38 pages, 16 figures. Updated with additional experiments |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2402.05468 |
| رقم الأكسشن: | edsarx.2402.05468 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |