Learning and Control Beyond Linearity: Towards a Non-asymptotic Theory for Bilinear Systems
eess.SY, cs.LG, cs.RO, cs.SY, math.OC, stat.ML
Submitted: 2026-09-16
Updated: 2026-09-26
License: http://creativecommons.org/licenses/by/4.0/
The gist: This tutorial provides a unified view of the emerging area of bilinear learning and control.
Terminology
Abstract
This tutorial provides a unified view of the emerging area of bilinear learning and control. Using linear systems as a benchmark, it explains what fundamentally changes in the bilinear settings, how recent theory addresses finite-sample learning and control, and how these ideas connect to broader themes in nonlinear control, representation learning, and data-driven decision making. For learning, we emphasize tools that are particularly useful in the bilinear settings, such as one-sided Bernstein's inequality for dependent and heavy-tailed covariates, blocking arguments, and martingale concentration for input-dependent noise. We then apply these tools to obtain finite-sample learning guarantees for fully observed bilinear systems, partially observed bilinear systems, and linear systems with bilinear observations. For control, we discuss quadratic control from bilinear observations, where the classical separation principle fails, and review tractable approaches based on belief-space receding horizon control. We also cover stabilization of bilinear dynamics under state feedback using semi-definite programming, LMI relaxations, sum-of-squares methods, and Koopman-based lifting. We conclude by discussing connections to reinforcement learning and machine learning, and some open problems in combined learning and control of bilinear systems.
Sources
- Dual Control of Linear Systems from Bilinear Observations with Belief Space Model Predictive Control
- Explore-then-Commit for Nonstationary Linear Bandits with Latent Dynamics
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Learning Koopman Models From Data Under General Noise Conditions
- Local Stability and Stabilization of Quadratic-Bilinear Systems using Petersen's Lemma
- Bounding the smallest singular value of a random matrix without concentration
- Reinforcement Learning with Fast Stabilization in Linear Dynamical Systems
- Probabilistic Formulations for System Identification of Linear Dynamics with Bilinear Observation Models
- SOSTOOLS Version 4.00 Sum of Squares Optimization Toolbox for MATLAB
- High-Dimensional Statistics
- Koopman-Assisted Reinforcement Learning
- Near optimal finite time identification of arbitrary linear dynamical systems
- Learning Linear Dynamics from Bilinear Observations
- Finite Sample Identification of Partially Observed Bilinear Dynamical Systems
- Proximal Policy Optimization Algorithms
- Koopman meets input-output data: Data-driven output-feedback control of nonlinear systems with closed-loop guarantees
- Non-Asymptotic Analysis of Robust Control from Coarse-Grained Identification
- Introduction to the non-asymptotic analysis of random matrices
- AdaJEPA: An Adaptive Latent World Model
- A Koopman Set-Membership Approach for Nonlinear Data-Driven Control with Stability Guarantees
Related papers
- One Request, Multiple Experts: LLM Orchestrates Domain Specific Models via Adaptive Task Routing
- A Geometric Decision Procedure for STL Feasibility and Repair
- Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
- Policy-Level Recursive Self-Improvement for Embodied AI with a Criticality World Model
- Minimal Experiments for Robust Stabilization: Information, Spectral Geometry, and Duration
- Decentralized Power-Optimal Coordination for Spacecraft Swarms Using Time-Varying Magnetorquer Actuation