Shetty, N and Bandla, M and Neema, N and Asokan, S and Seelamantula, CS (2024) MOMENTUM-IMBUED LANGEVIN DYNAMICS (MILD) FOR FASTER SAMPLING. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2024, 14 - 19 April 2024, Seoul, pp. 6635-6639.
![]() |
PDF
iee_int_con_aco_spe._sig._pro._pro._2024.3.pdf - Published Version Restricted to Registered users only Download (2MB) | Request a copy |
Abstract
Score-based generative models have emerged as the state-of-the-art in generative modeling. In this paper, we introduce a novel sampling scheme that can be combined with pre-trained score-based diffusion models to speed up sampling by a factor of two to five in terms of the number of function evaluations (NFEs) with a superior Fréchet Inception distance (FID), compared to Annealed Langevin dynamics in noise-conditional score network (NCSN) and improved noise-conditional score network (NCSN++). The proposed sampling algorithm is inspired by momentum-based accelerated gradient descent used in convex optimization techniques. We validate the sampling efficiency of the proposed algorithm in terms of FID on CIFAR-10 and CelebA datasets. © 2024 IEEE.
Item Type: | Conference Paper |
---|---|
Publication: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings |
Publisher: | Institute of Electrical and Electronics Engineers Inc. |
Additional Information: | The copyright for this article belongs to Institute of Electrical and Electronics Engineers Inc. |
Department/Centre: | Division of Electrical Sciences > Computer Science & Automation Division of Electrical Sciences > Electrical Engineering |
Date Deposited: | 19 Aug 2024 10:25 |
Last Modified: | 19 Aug 2024 10:25 |
URI: | http://eprints.iisc.ac.in/id/eprint/85472 |
Actions (login required)
![]() |
View Item |