Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models
By: Heiko Oppel, Andreas Spilz, Michael Munz
Potential Business Impact:
Makes AI create data much faster and better.
Denoising Diffusion Probabilistic Models (DDPMs) can generate synthetic timeseries data to help improve the performance of a classifier, but their sampling process is computationally expensive. We address this by combining implicit diffusion models with a novel Sawtooth Sampler that accelerates the reverse process and can be applied to any pretrained diffusion model. Our approach achieves a 30 times speed-up over the standard baseline while also enhancing the quality of the generated sequences for classification tasks.
Similar Papers
Sublinear iterations can suffice even for DDPMs
Machine Learning (CS)
Makes AI create better pictures using less math.
Diffusion-Based Generation and Imputation of Driving Scenarios from Limited Vehicle CAN Data
Machine Learning (CS)
Makes car data better for training computers.
Diffusion Models are Molecular Dynamics Simulators
Machine Learning (CS)
Simulates molecules moving like real life.