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

Daigo Fujiwara; Tomonori Izumitani; Shohei Shimizu

IJCAI 20260 citations

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

Daigo Fujiwara, Tomonori Izumitani, Shohei Shimizu

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.

Uncertainty in AI: Causality, structural causal models and causal inferenceUncertainty in AI: Sequential decision making

BibTeX

@inproceedings{ijcai2026_causalnewtonopti,
  title = {Causal Newton Optimization: Online Calibration with Iterative Local Linear Modeling and Newton Updates},
  author = {Daigo Fujiwara and Tomonori Izumitani and Shohei Shimizu},
  booktitle = {IJCAI 2026},
  year = {2026}
}