RINS-T: Robust Implicit Neural Solvers for Time Series Linear Inverse Problems

2025-10-20

AI Summary

Time-series signals are frequently corrupted by missing values, noise, and outliers, posing significant challenges for accurate signal recovery; moreover, existing deep learning approaches rely heavily on large-scale pretraining and exhibit poor generalization. To address these limitations, we propose RINS-T—a pretrained-free deep prior framework for robust time-series reconstruction. RINS-T employs a lightweight neural network as an implicit prior and integrates robust optimization to relax the restrictive Gaussian noise assumption. We introduce three key innovations: (i) guided input initialization, (ii) input perturbation, and (iii) convex output combination—collectively enhancing optimization stability and outlier resilience. The framework adopts unsupervised end-to-end learning, enabling universal signal reconstruction without task-specific supervision. Extensive experiments across diverse real-world scenarios demonstrate that RINS-T consistently outperforms classical methods and state-of-the-art deep models, achieving superior generalization and practical applicability.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Search and Optimization: Learning to Search
• Intelligent Robots: State Estimation

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

Time series data are often affected by various forms of corruption, such as missing values, noise, and outliers, which pose significant challenges for tasks such as forecasting and anomaly detection. To address these issues, inverse problems focus on reconstructing the original signal from corrupted data by leveraging prior knowledge about its underlying structure. While deep learning methods have demonstrated potential in this domain, they often require extensive pretraining and struggle to generalize under distribution shifts. In this work, we propose RINS-T (Robust Implicit Neural Solvers for Time Series Linear Inverse Problems), a novel deep prior framework that achieves high recovery performance without requiring pretraining data. RINS-T leverages neural networks as implicit priors and integrates robust optimization techniques, making it resilient to outliers while relaxing the reliance on Gaussian noise assumptions. To further improve optimization stability and robustness, we introduce three key innovations: guided input initialization, input perturbation, and convex output combination techniques. Each of these contributions strengthens the framework's optimization stability and robustness. These advancements make RINS-T a flexible and effective solution for addressing complex real-world time series challenges. Our code is available at https://github.com/EPFL-IMOS/RINS-T.

Problem

• Reconstructing corrupted time series data with missing values and outliers
• Overcoming deep learning limitations in generalization without pretraining
• Developing robust optimization techniques for stable signal recovery

Innovation

• Implicit neural priors without pretraining data
• Robust optimization resilient to outliers
• Guided initialization and perturbation techniques