paper-with-me

Papers

Analyzing and Improving Diffusion Models for Time-Series Data Imputation: A Proximal Recursion Perspective

2026-02-01 · Zhichao Chen, Hao Wang, Fangyikang Wang, Licheng Pan, Zhengnan Li, Yunfei Teng, Haoxuan Li, Zhouchen Lin arxiv

Diffusion models (DMs) have shown promise for Time-Series Data Imputation (TSDI); however, their performance remains inconsistent in complex scenarios. We attribute this to two primary obstacles: (1) non-stationary temporal dynamics, which can bias the inference trajectory and lead to outlier-sensitive imputations; and (2) objective inconsistency, since imputation favors accurate pointwise recovery whereas DMs are inherently trained to generate diverse samples. To better understand these issues, we analyze DM-based TSDI process through a proximal-operator perspective and uncover that an implicit Wasserstein distance regularization inherent in the process hinders the model's ability to counteract non-stationarity and dissipative regularizer, thereby amplifying diversity at the expense of fidelity. Building on this insight, we propose a novel framework called SPIRIT (Semi-Proximal Transport Regularized time-series Imputation). Specifically, we introduce entropy-induced Bregman divergence to relax the mass preserving constraint in the Wasserstein distance, formulate the semi-proximal transport (SPT) discrepancy, and theoretically prove the robustness of SPT against non-stationarity. Subsequently, we remove the dissipative structure and derive the complete SPIRIT workflow, with SPT serving as the proximal operator. Extensive experiments demonstrate the effectiveness of the proposed SPIRIT approach.

📄 PDF Abstract BibTeX arXiv:2602.01182

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation

2021-07-07 · NeurIPS 2021 12 · Yusuke Tashiro, Jiaming Song, Yang song, Stefano Ermon

The imputation of missing values in time series has many applications in healthcare and finance. While autoregressive models are natural candidates for time series imputation, score-based diffusion models have recently o…

Audio SynthesisImage GenerationImputationMissing Values+2

sasdim: self-adaptive noise scaling diffusion model for spatial time series imputation

2023-09-05 · Shunyang Zhang, Senzhang Wang, Xianzhen Tan, Ruochen Liu 외

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 Series

Discretizing Continuous Time Series for Imputation with Masked Diffusion Training

2026-08-19 · Dongbin Kim, Seungyun Lee, Geonwoo Shin, Jaewook Lee arxiv

Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitati…

Time Series Analysis

DiffImp: Efficient Diffusion Model for Probabilistic Time Series Imputation with Bidirectional Mamba Backbone

2024-10-17 · Hongfan Gao, Wangmeng Shen, Xiangfei Qiu, Ronghui Xu 외

Probabilistic time series imputation has been widely applied in real-world scenarios due to its ability to estimate uncertainty of imputation results. Meanwhile, denoising diffusion probabilistic models (DDPMs) have achi…

DenoisingImputationMambaTime Series

MTSCI: A Conditional Diffusion Model for Multivariate Time Series Consistent Imputation

2024-08-11 · Jianping Zhou, Junhao Li, Guanjie Zheng, Xinbing Wang 외

Missing values are prevalent in multivariate time series, compromising the integrity of analyses and degrading the performance of downstream tasks. Consequently, research has focused on multivariate time series imputatio…

DenoisingImputationInductive BiasMissing Values+2