Proceedings

Causal Newton Optimization: Online Calibration with Iterative Local Linear Modeling and Newton Updates

Daigo Fujiwara, Tomonori Izumitani, Shohei Shimizu

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 6380-6388.

https://doi.org/10.24963/ijcai.2026/710

Keywords

  • Machine Learning: Optimization
  • AI Ethics, Trust, Fairnes: Safety and robustness
  • Machine Learning: Online learning
  • Uncertainty in AI: Causality, structural causal models and causal inference

Abstract

Optimization in industrial systems often involves calibrating from a semi-optimized state, where global exploration methods like Reinforcement Learning (RL) or Bayesian Optimization (BO) are inefficient or unsafe. We propose Causal Newton Optimization (CNO), an online algorithm that iteratively calibrates inputs under a known causal graph but unknown structural equations. CNO estimates local linear causal effects via additive interventions and employs a log-linear variance regression to robustly guide Newton-based updates. Evaluations on synthetic systems and a chemical plant simulator demonstrate that CNO achieves the best balance between objective improvement and robustness. While traditional PID control suits standard dynamical systems, CNO significantly outperforms RL and BO in complex structural causal models, providing the robust stability vital for safety-critical real-world applications.

Daigo Fujiwara, Tomonori Izumitani, and Shohei Shimizu. 2026. Causal Newton Optimization: Online Calibration with Iterative Local Linear Modeling and Newton Updates. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 6380–6388. https://doi.org/10.24963/ijcai.2026/710
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards