{"ID":2836373,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21320","arxiv_id":"2511.21320","title":"Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2511.21320","url_pdf":"https://arxiv.org/pdf/2511.21320v1","authors":"[\"Heiko Oppel\",\"Andreas Spilz\",\"Michael Munz\"]","published":"2025-11-26T12:05:44Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}