Abstract
We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. This result extends the work of Hand and Voroninski from efficient inversion to efficient posterior sampling. In practice, to allow for increased expressivity, we propose to do posterior sampling in the latent space of a pre-trained generative model. To achieve that, we train a score-based model in the latent space of a StyleGAN-2 and we use it to solve inverse problems. Our framework, Score-Guided Intermediate Layer Optimization (SGILO), extends prior work by replacing the sparsity regularization with a generative prior in the intermediate layer. Experimentally, we obtain significant improvements over the previous state-of-the-art, especially in the low measurement regime.
Original language | English |
---|---|
Pages (from-to) | 4722-4753 |
Number of pages | 32 |
Journal | Proceedings of Machine Learning Research |
Volume | 162 |
State | Published - 2022 |
Externally published | Yes |
Event | 39th International Conference on Machine Learning, ICML 2022 - Baltimore, United States Duration: 17 Jul 2022 → 23 Jul 2022 https://proceedings.mlr.press/v162/ |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Software
- Control and Systems Engineering
- Statistics and Probability