Sawtooth Sampling for Time Series Denoising Diffusion Implicit Models

📅 2025-11-26
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
To address the low sampling efficiency and high computational cost of diffusion models in time-series synthesis, this paper proposes a general-purpose acceleration framework based on implicit diffusion modeling. We introduce a novel Sawtooth sampler that accelerates the denoising process without modifying pre-trained models. The sampler employs non-uniform step-size scheduling and gradient-guided trajectory optimization to reduce the number of iterations while preserving generation fidelity. Evaluated on standard time-series benchmarks, our method achieves an average 30× speedup over vanilla DDPM, with generated samples exhibiting superior statistical similarity and higher downstream classification accuracy compared to both DDPM and state-of-the-art acceleration baselines. Our key contribution lies in the first integration of implicit diffusion with structured sampling strategies—achieving a favorable trade-off among inference efficiency, sample quality, and model-agnostic applicability.

Technology Category

Application Category

📝 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.
Problem

Research questions and friction points this paper is trying to address.

Accelerating slow sampling in diffusion models for time series generation
Improving synthetic data quality for time series classification tasks
Enhancing computational efficiency of pretrained diffusion model inference
Innovation

Methods, ideas, or system contributions that make the work stand out.

Combining implicit diffusion models with Sawtooth Sampler
Accelerating reverse process for pretrained diffusion models
Achieving 30 times speed-up while enhancing quality
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
H
Heiko Oppel
AI for Sensor Data Analytics Research Group, Ulm University of Applied Sciences
A
Andreas Spilz
AI for Sensor Data Analytics Research Group, Ulm University of Applied Sciences
M
Michael Munz
AI for Sensor Data Analytics Research Group, Ulm University of Applied Sciences