Multivariate time series (MTS) imputation is often compromised by mismatch between observed and true data distributions -- a bias exacerbated by non-stationarity and systematic missingness. Standard methods that minimize reconstruction error or encourage distributional alignment risk overfitting these biased observations. We propose the Distributionally Robust Regularized Imputer Objective (DRIO), which jointly minimizes reconstruction error and the divergence between the imputer and a worst-case distribution within a Wasserstein ambiguity set. We derive a tractable dual formulation that reduces infinite-dimensional optimization over measures to adversarial search over sample trajectories, and propose an adversarial learning algorithm compatible with flexible deep learning backbones. Comprehensive experiments on diverse real-world datasets show DRIO consistently improves imputation under both missing-completely-at-random and missing-not-at-random settings, reaching Pareto-optimal trade-offs between reconstruction accuracy and distributional alignment.

翻译：多元时间序列（MTS）插补常因观测数据分布与真实数据分布不匹配而受到影响——这种偏差在非平稳性和系统性缺失的情况下会进一步加剧。最小化重构误差或促进分布对齐的标准方法存在对这些有偏观测过拟合的风险。我们提出了分布鲁棒正则化插补目标（DRIO），它联合最小化重构误差以及插补器与Wasserstein模糊集内最坏情况分布之间的散度。我们推导出一个可处理的对偶形式，将测度上的无限维优化简化为样本轨迹上的对抗性搜索，并提出了一种与灵活深度学习主干网络兼容的对抗学习算法。在多样化的真实世界数据集上的综合实验表明，DRIO在完全随机缺失和非随机缺失设置下均能持续改进插补效果，在重构精度与分布对齐之间达到了帕累托最优权衡。