Exact Recovery Guarantees for Parameterized Non-linear System Identification Problem under Adversarial Attacks

• URL: http://arxiv.org/abs/2409.00276v2
• Date: Mon, 16 Sep 2024 01:41:17 GMT
• Title: Exact Recovery Guarantees for Parameterized Non-linear System Identification Problem under Adversarial Attacks
• Authors: Haixiang Zhang, Baturalp Yalcin, Javad Lavaei, Eduardo D. Sontag,
• Abstract summary: We study the system identification problem for parameterized non-linear systems using basis functions under adversarial attacks. Motivated by the LASSO-type estimators, we analyze the exact recovery property of a non-smooth estimator. This is the first study on the sample complexity analysis of a non-smooth estimator for the non-linear system identification problem.
• Score: 16.705631360131886
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this work, we study the system identification problem for parameterized non-linear systems using basis functions under adversarial attacks. Motivated by the LASSO-type estimators, we analyze the exact recovery property of a non-smooth estimator, which is generated by solving an embedded $\ell_1$-loss minimization problem. First, we derive necessary and sufficient conditions for the well-specifiedness of the estimator and the uniqueness of global solutions to the underlying optimization problem. Next, we provide exact recovery guarantees for the estimator under two different scenarios of boundedness and Lipschitz continuity of the basis functions. The non-asymptotic exact recovery is guaranteed with high probability, even when there are more severely corrupted data than clean data. Finally, we numerically illustrate the validity of our theory. This is the first study on the sample complexity analysis of a non-smooth estimator for the non-linear system identification problem.

Related papers

• Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum [56.37522020675243]
  We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. We show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks.
  arXiv  Detail & Related papers  (2024-10-22T10:19:27Z)
• A least-square method for non-asymptotic identification in linear switching control [17.938732931331064]
  It is known that the underlying partially-observed linear dynamical system lies within a finite collection of known candidate models. We characterize the finite-time sample complexity of this problem by leveraging recent advances in the non-asymptotic analysis of linear least-square methods. We propose a data-driven switching strategy that identifies the unknown parameters of the underlying system.
  arXiv  Detail & Related papers  (2024-04-11T20:55:38Z)
• Global Convergence of Online Identification for Mixed Linear Regression [1.9295130374196499]
  Mixed linear regression (MLR) is a powerful model for characterizing nonlinear relationships. This paper investigates the online identification and data clustering problems for two basic classes of MLRs. It introduces two corresponding new online identification algorithms based on the expectation-maximization principle.
  arXiv  Detail & Related papers  (2023-11-30T12:30:42Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• A Learning-Based Optimal Uncertainty Quantification Method and Its Application to Ballistic Impact Problems [1.713291434132985]
  This paper concerns the optimal (supremum and infimum) uncertainty bounds for systems where the input (or prior) measure is only partially/imperfectly known. We demonstrate the learning based framework on the uncertainty optimization problem. We show that the approach can be used to construct maps for the performance certificate and safety in engineering practice.
  arXiv  Detail & Related papers  (2022-12-28T14:30:53Z)
• Robust identification of non-autonomous dynamical systems using stochastic dynamics models [0.0]
  This paper considers the problem of system identification (ID) of linear and nonlinear non-autonomous systems from noisy and sparse data. We propose and analyze an objective function derived from a Bayesian formulation for learning a hidden Markov model. We show that our proposed approach has improved smoothness and inherent regularization that make it well-suited for system ID.
  arXiv  Detail & Related papers  (2022-12-20T16:36:23Z)
• Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems [62.83783246648714]
  We propose a sequential quadratic programming algorithm (TR-StoSQP) to solve nonlinear optimization problems with objectives and deterministic equality constraints. The algorithm adaptively selects the trust-region radius and, compared to the existing line-search StoSQP schemes, allows us to utilize indefinite Hessian matrices.
  arXiv  Detail & Related papers  (2022-11-29T05:52:17Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• A general sample complexity analysis of vanilla policy gradient [101.16957584135767]
  Policy gradient (PG) is one of the most popular reinforcement learning (RL) problems. "vanilla" theoretical understanding of PG trajectory is one of the most popular methods for solving RL problems.
  arXiv  Detail & Related papers  (2021-07-23T19:38:17Z)
• Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors [12.798687476698063]
  We study an alternative prior where the low-rank component is in the range of a trained generative network. We establish a favorable global optimization landscape for a nonlinear least squares objective. This result suggests that generative priors have no computational-to-statistical gap for structured rank-one matrix recovery.
  arXiv  Detail & Related papers  (2020-06-14T16:46:16Z)
• On dissipative symplectic integration with applications to gradient-based optimization [77.34726150561087]
  We propose a geometric framework in which discretizations can be realized systematically. We show that a generalization of symplectic to nonconservative and in particular dissipative Hamiltonian systems is able to preserve rates of convergence up to a controlled error.
  arXiv  Detail & Related papers  (2020-04-15T00:36:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.