Fourier analysis has been an instrumental tool in the development of signal processing. This leads us to wonder whether this framework could similarly benefit generative modelling. In this paper, we explore this question through the scope of time series diffusion models. More specifically, we analyze whether representing time series in the frequency domain is a useful inductive bias for score-based diffusion models. By starting from the canonical SDE formulation of diffusion in the time domain, we show that a dual diffusion process occurs in the frequency domain with an important nuance: Brownian motions are replaced by what we call mirrored Brownian motions, characterized by mirror symmetries among their components. Building on this insight, we show how to adapt the denoising score matching approach to implement diffusion models in the frequency domain. This results in frequency diffusion models, which we compare to canonical time diffusion models. Our empirical evaluation on real-world datasets, covering various domains like healthcare and finance, shows that frequency diffusion models better capture the training distribution than time diffusion models. We explain this observation by showing that time series from these datasets tend to be more localized in the frequency domain than in the time domain, which makes them easier to model in the former case. All our observations point towards impactful synergies between Fourier analysis and diffusion models.
T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Models
Xidian University(西安电子科技大学);Griffith University(格里菲斯大学);Yunnan University(云南大学);Carnegie Mellon University(卡内基梅隆大学);Zhejiang University(浙江大学);Augusta University(奥古斯塔大学);The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
Time Series Similarity Score Functions to Monitor and Interact with the Training and Denoising Process of a Time Series Diffusion Model applied to a Human Activity Recognition Dataset based on IMUs
AI for Sensor Data Analytics Research Group, Ulm University of Applied Sciences(人工智能传感器数据解析研究组,乌尔姆应用科学大学)
A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
University of Oxford(牛津大学);Griffith University(格里菲斯大学);Carnegie Mellon University(卡内基梅隆大学);Zhejiang Normal University(浙江师范大学);Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州));The University of Hong Kong(香港大学);Salesforce Research(Salesforce研究);East China Normal University(东华大学);Fudan University(复旦大学)
A diffusion-based generative model for financial time series via geometric Brownian motion
Department of Mathematics, POSTECH(POSTECH数学系);Department of Financial Mathematics, Gachon University(高丽大学金融数学系);Department of Applied Artificial Intelligence, SeoulTech(首尔科技大学应用人工智能系)
Time Series Diffusion Method: A Denoising Diffusion Probabilistic Model for Vibration Signal Generation
Harbin Institute of Technology(哈尔滨工业大学);Menoufia University(梅努菲亚大学);Lodz University of Technology(罗兹技术大学);Galala University(加拉拉大学);Shenyang Blower Works Group Corporation(沈阳鼓风机集团股份有限公司)
Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation
Central South University(中南大学);Aalborg University(奥尔堡大学);The Hong Kong Polytechnic University(香港理工大学);National University of Defense Technology(国防科技大学)
Parallel Complex Diffusion for Scalable Time Series Generation
Institute of Cyber-Systems and Control(网络系统与控制研究所);Zhejiang University(浙江大学);Griffith University(格里菲斯大学);School of Mathematics(数学学院);Southeast University(东南大学);Squirrel Ai Learning
Boundary-enhanced time series data imputation with long-term dependency diffusion models
Henan University(河南大学);Yangtze Delta Region Institute (Quzhou), University of Electronic Science and Technology of China(电子科技大学长三角研究院(衢州));University College London(伦敦大学学院)
High-Frequency Space Diffusion Models for Accelerated MRI
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);University of Chinese Academy of Sciences(中国科学院大学);Shenzhen University(深圳大学);Pazhou Lab(琶洲实验室)
RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion
Tsinghua University(清华大学);The University of Hong Kong(香港大学);Beijing University of Posts and Telecommunications(北京邮电大学);Huawei Technologies Co., Ltd(华为技术有限公司)
School of AIA, Huazhong University of Science and Technology(华中科技大学AIA学院);Department of Computer Science and Engineering, Shanghai Jiao Tong University(上海交通大学计算机科学与工程系);Center for Applied Statistics and School of Statistics, Renmin University of China(中国人民大学应用统计中心及统计学院);School of EIC, Huazhong University of Science and Technology(华中科技大学EIC学院)
Stochastic Diffusion: A Diffusion Probabilistic Model for Stochastic Time Series Forecasting
School of Computing and Information Systems, The University of Melbourne(计算与信息系统学院,墨尔本大学);Department of Surgery (Otolaryngology), The University of Melbourne(外科部门(耳鼻喉科),墨尔本大学);School of Mathematics and Statistics, The University of Melbourne(数学与统计学学院,墨尔本大学)