Diffusion Transformers for Imputation: Statistical Efficiency and Uncertainty Quantification
Imputation methods play a critical role in enhancing the quality of practical time-series data, which often suffer from pervasive missing values. Recently, diffusion-based generative imputation methods have demonstrated remarkable success compared to autoregressive and conventional statistical approaches. Despite their empirical success, the theoretical understanding of how well diffusion-based models capture complex spatial and temporal dependencies between the missing values and observed ones remains limited. Our work addresses this gap by investigating the statistical efficiency of conditional diffusion transformers for imputation and quantifying the uncertainty in missing values. Specifically, we derive statistical sample complexity bounds based on a novel approximation theory for conditional score functions using transformers, and, through this, construct tight confidence regions for missing values. Our findings also reveal that the efficiency and accuracy of imputation are significantly influenced by the missing patterns. Furthermore, we validate these theoretical insights through simulation and propose a mixed-masking training strategy to enhance the imputation performance.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Latent Space Score-based Diffusion Model for Probabilistic Multivariate Time Series Imputation
Accurate imputation is essential for the reliability and success of downstream tasks. Recently, diffusion models have attracted great attention in this field. However, these models neglect the latent distribution in a lo…
ImputationMultivariate Time Series ImputationTime SeriesDiffusion Models for Tabular Data Imputation and Synthetic Data Generation
Data imputation and data generation have important applications for many domains, like healthcare and finance, where incomplete or missing data can hinder accurate analysis and decision-making. Diffusion models have emer…
DecoderDenoisingImputationSynthetic Data GenerationMultiple Imputation via Generative Adversarial Network for High-dimensional Blockwise Missing Value Problems
Missing data are present in most real world problems and need careful handling to preserve the prediction accuracy and statistical consistency in the downstream analysis. As the gold standard of handling missing data, mu…
Generative Adversarial NetworkImputationsasdim: self-adaptive noise scaling diffusion model for spatial time series imputation
Spatial time series imputation is critically important to many real applications such as intelligent transportation and air quality monitoring. Although recent transformer and diffusion model based approaches have achiev…
ImputationTime SeriesRecurrent Interpolants for Probabilistic Time Series Prediction
Sequential models like recurrent neural networks and transformers have become standard for probabilistic multivariate time series forecasting across various domains. Despite their strengths, they struggle with capturing …
Computational EfficiencyImputationMultivariate Time Series ForecastingPrediction+3