Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds

Item #:

085713-0657

Details

DOI: https://doi.org/10.52202/085713-0657
Author(s): Vahan Arsenyan, Elen Vardanyan, Arnak Dalalyan
Pages: 22153-22196 (44 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-0657
Author(s): Vahan Arsenyan, Elen Vardanyan, Arnak Dalalyan
Pages: 22153-22196 (44 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)