LSCD: Lomb-Scargle Conditioned Diffusion for Time series Imputation

2025/06/20 by Fons, Elizabeth, Sztrajman, Alejandro, El-Laham, Yousef +3 · 1 citation
Computer Science · Neuroscience · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning in Healthcare

paper · pdf · doi:10.48550/arxiv.2506.17039

openalex publication_date 2025/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Time series with missing or irregularly sampled data are a persistent challenge in machine learning. Many methods operate on the frequency-domain, relying on the Fast Fourier Transform (FFT) which assumes uniform sampling, therefore requiring prior interpolation that can distort the spectra. To address this limitation, we introduce a differentiable Lomb--Scargle layer that enables a reliable computation of the power spectrum of irregularly sampled data. We integrate this layer into a novel score-based diffusion model (LSCD) for time series imputation conditioned on the entire signal spectrum. Experiments on synthetic and real-world benchmarks demonstrate that our method recovers missing data more accurately than purely time-domain baselines, while simultaneously producing consistent frequency estimates. Crucially, our method can be easily integrated into learning frameworks, enabling broader adoption of spectral guidance in machine learning approaches involving incomplete or irregular data.

Citations

• Variational Neural Stochastic Differential Equations with Change Points
• A Survey on Diffusion Models for Time Series and Spatio-Temporal Data
• Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
• Time Series Diffusion in the Frequency Domain
• MADS: Modulated Auto-Decoding SIREN for time series imputation
• Neural Continuous-Discrete State Space Models for Irregularly-Sampled Time Series
• Learning from data with structured missingness
• Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion
• TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
• HyperTime: Implicit Neural Representation for Time Series
• SAITS: Self-attention-based imputation for time series
• Modeling Irregular Time Series with Continuous Recurrent Units
• Neural Flows: Efficient Alternative to Neural ODEs
• CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation
• Score-Based Generative Modeling through Stochastic Differential Equations
• Denoising Diffusion Probabilistic Models
• Multi-Time Attention Networks for Irregularly Sampled Time Series
• Neural Controlled Differential Equations for Irregular Time Series
• Generative Modeling by Estimating Gradients of the Data Distribution
• GP-VAE: Deep Probabilistic Time Series Imputation
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
• Conditional Neural Processes
• BRITS: Bidirectional Recurrent Imputation for Time Series
• Understanding the Lomb–Scargle Periodogram
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Missing Data: A Comparison of Neural Network and Expectation Maximisation Techniques
• Studies in astronomical time series analysis. II - Statistical aspects of spectral analysis of unevenly spaced data
• Least-squares frequency analysis of unequally spaced data

Cited by

• FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation

Related

• FADTI: Fourier and Attention Driven Diffusion for Multivariate Time Series Imputation
• Score-CDM: Score-Weighted Convolutional Diffusion Model for Multivariate Time Series Imputation
• Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
• Cross-Domain Conditional Diffusion Models for Time Series Imputation
• Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation