@inproceedings{discovery10198875,
           month = {January},
          series = {ICLR},
            year = {2024},
           title = {Conditional Variational Diffusion Models},
       publisher = {International Conference on Learning Representations (ICLR)},
         journal = {12th International Conference on Learning Representations, ICLR 2024},
          volume = {2024},
            note = {This version is the version of record. For information on re-use, please refer to the publisher's terms and conditions.},
       booktitle = {12th International Conference on Learning Representations, ICLR 2024},
        keywords = {Denoising Diffusion Probabilistic Models, Inverse Problems, Generative Models, Super Resolution, Phase Quantification, Variational Methods},
             url = {https://openreview.net/forum?id=YOKnEkIuoi},
          author = {della Maggiora, G and Croquevielle, LA and Deshpande, N and Horsley, H and Heinis, T and Yakimovich, A},
        abstract = {Inverse problems aim to determine parameters from observations, a crucial task in engineering and science. Lately, generative models, especially diffusion models, have gained popularity in this area for their ability to produce realistic solutions and their good mathematical properties. Despite their success, an important drawback of diffusion models is their sensitivity to the choice of variance schedule, which controls the dynamics of the diffusion process. Fine-tuning this schedule for specific applications is crucial but time-consuming and does not guarantee an optimal result. We propose a novel approach for learning the schedule as part of the training process. Our method supports probabilistic conditioning on data, provides high-quality solutions, and is flexible, proving able to adapt to different applications with minimum overhead. This approach is tested in two unrelated inverse problems: super-resolution microscopy and quantitative phase imaging, yielding comparable or superior results to previous methods and fine-tuned diffusion models. We conclude that fine-tuning the schedule by experimentation should be avoided because it can be learned during training in a stable way that yields better results.}
}