Gradient-Based Adaptive Prediction and Control for Nonlinear Dynamical Systems

This paper investigates gradient-based adaptive prediction and control for nonlinear stochastic dynamical systems under a weak convexity condition on the prediction-based loss. This condition accommodates a broad range of nonlinear models in control and machine learning such as saturation functions, sigmoid, ReLU and tanh activation functions, and standard classification models. Without requiring any persistent excitation of the data, we establish global convergence of the proposed adaptive predictor and derive explicit rates for its asymptotic performance. Furthermore, under a classical nonlinear minimum-phase condition and with a linear growth bound on the nonlinearities, we establish the convergence rate of the resulting closed-loop control error. Finally, we demonstrate the effectiveness of the proposed adaptive prediction algorithm on a real-world judicial sentencing dataset. The adaptive control performance will also be evaluated via a numerical simulation.

• Publication year

  2026

• Venue

  Unknown venue

• Publication date

  2026-02-12

• Fields of study

  Computer Science, Engineering

• Identifiers
  arXiv 2602.11899
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Judicial Sentencing Prediction Based on Hybrid Models and Two-Stage Learning Algorithms

  2025cited by this paper
• A Class of Convex Optimization-Based Recursive Algorithms for Identification of Stochastic Systems

  2024cited by this paper
• Feedback and uncertainty: Some basic problems and results

  2020influential reference
• Towards Theoretically Understanding Why SGD Generalizes Better Than ADAM in Deep Learning

  2020cited by this paper
• On the Power of Over-parametrization in Neural Networks with Quadratic Activation

  2018cited by this paper
• Optimization Methods for Large-Scale Machine Learning

  2016cited by this paper
• Gradient Descent Learns Linear Dynamical Systems

  2016cited by this paper
• Beyond Convexity: Stochastic Quasi-Convex Optimization

  2015cited by this paper
• Logarithmic regret algorithms for online convex optimization

  2006cited by this paper
• Pattern Recognition and Machine Learning

  2006cited by this paper
• Sparseness of Support Vector Machines

  2003cited by this paper
• Adaptive control of discrete-time nonlinear systems with structural uncertainties

  2000influential reference
• Convergence and logarithm laws of self-tuning regulators

  1995cited by this paper
• Adaptive Control

  1993cited by this paper
• Identification and Stochastic Adaptive Control

  1991cited by this paper
• Strong consistency of recursive identification by no use of persistent excitation condition

  1985influential reference
• Adaptive filtering prediction and control

  1984cited by this paper
• Discrete time stochastic adaptive control

  1979cited by this paper
• International Journal of Adaptive Control and Signal Processing Aftertreatment Control and Adaptation for Automotive Lean Burn Engines with Hego Sensors

  year unknowncited by this paper

• No citing papers are available for this paper.