Research

Paper

TESTING March 12, 2026

Conformalized Data-Driven Reachability Analysis with PAC Guarantees

Authors

Yanliang Huang, Zhen Zhang, Peng Xie, Zhuoqi Zeng, Amr Alanwar

Abstract

Data-driven reachability analysis computes over-approximations of reachable sets directly from noisy data. Existing deterministic methods require either known noise bounds or system-specific structural parameters such as Lipschitz constants. We propose Conformalized Data-Driven Reachability (CDDR), a framework that provides Probably Approximately Correct (PAC) coverage guarantees through the Learn Then Test (LTT) calibration procedure, requiring only that calibration trajectories be independently and identically distributed. CDDR is developed for three settings: linear time-invariant (LTI) systems with unknown process noise distributions, LTI systems with bounded measurement noise, and general nonlinear systems including non-Lipschitz dynamics. Experiments on a 5-dimensional LTI system under Gaussian and heavy-tailed Student-t noise and on a 2-dimensional non-Lipschitz system with fractional damping demonstrate that CDDR achieves valid coverage where deterministic methods do not provide formal guarantees. Under anisotropic noise, a normalized score function reduces the reachable set volume while preserving the PAC guarantee.

Metadata

arXiv ID: 2603.12220
Provider: ARXIV
Primary Category: eess.SY
Published: 2026-03-12
Fetched: 2026-03-13 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.12220v1</id>\n    <title>Conformalized Data-Driven Reachability Analysis with PAC Guarantees</title>\n    <updated>2026-03-12T17:45:10Z</updated>\n    <link href='https://arxiv.org/abs/2603.12220v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.12220v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Data-driven reachability analysis computes over-approximations of reachable sets directly from noisy data. Existing deterministic methods require either known noise bounds or system-specific structural parameters such as Lipschitz constants. We propose Conformalized Data-Driven Reachability (CDDR), a framework that provides Probably Approximately Correct (PAC) coverage guarantees through the Learn Then Test (LTT) calibration procedure, requiring only that calibration trajectories be independently and identically distributed. CDDR is developed for three settings: linear time-invariant (LTI) systems with unknown process noise distributions, LTI systems with bounded measurement noise, and general nonlinear systems including non-Lipschitz dynamics. Experiments on a 5-dimensional LTI system under Gaussian and heavy-tailed Student-t noise and on a 2-dimensional non-Lipschitz system with fractional damping demonstrate that CDDR achieves valid coverage where deterministic methods do not provide formal guarantees. Under anisotropic noise, a normalized score function reduces the reachable set volume while preserving the PAC guarantee.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SY'/>\n    <published>2026-03-12T17:45:10Z</published>\n    <arxiv:primary_category term='eess.SY'/>\n    <author>\n      <name>Yanliang Huang</name>\n    </author>\n    <author>\n      <name>Zhen Zhang</name>\n    </author>\n    <author>\n      <name>Peng Xie</name>\n    </author>\n    <author>\n      <name>Zhuoqi Zeng</name>\n    </author>\n    <author>\n      <name>Amr Alanwar</name>\n    </author>\n  </entry>"
}