A finite-sample generalization bound for stable LPV systems

• URL: http://arxiv.org/abs/2405.10054v3
• Date: Tue, 21 May 2024 04:49:55 GMT
• Title: A finite-sample generalization bound for stable LPV systems
• Authors: Daniel Racz, Martin Gonzalez, Mihaly Petreczky, Andras Benczur, Balint Daroczy,
• Abstract summary: We derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: One of the main theoretical challenges in learning dynamical systems from data is providing upper bounds on the generalization error, that is, the difference between the expected prediction error and the empirical prediction error measured on some finite sample. In machine learning, a popular class of such bounds are the so-called Probably Approximately Correct (PAC) bounds. In this paper, we derive a PAC bound for stable continuous-time linear parameter-varying (LPV) systems. Our bound depends on the H2 norm of the chosen class of the LPV systems, but does not depend on the time interval for which the signals are considered.

Related papers

• PAC bounds of continuous Linear Parameter-Varying systems related to neural ODEs [0.0]
  We consider the problem of learning Neural Ordinary Differential Equations (neural ODEs) within the context of Linear -Varying (LPV) systems in continuous-time. We provide Probably Approximately Correct (PAC) bounds under stability for LPV systems related to neural ODEs.
  arXiv  Detail & Related papers  (2023-07-07T14:39:18Z)
• PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss [13.251009291060992]
  We derive a Probably Approxilmately Correct(PAC)-Bayesian error bound for linear time-invariant (LTI) dynamical systems with inputs. Such bounds are widespread in machine learning, and they are useful for characterizing the predictive power of models learned from finitely many data points.
  arXiv  Detail & Related papers  (2023-03-29T16:06:07Z)
• PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models [13.251009291060992]
  We derive a PAC-Bayesian-Like error bound for a class of dynamical systems with inputs. We discuss various consequences of this error bound.
  arXiv  Detail & Related papers  (2022-12-30T17:37:33Z)
• Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations [114.17826109037048]
  Ordinary Differential Equations (ODEs) have recently gained a lot of attention in machine learning. theoretical aspects, e.g., identifiability and properties of statistical estimation are still obscure. This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
  arXiv  Detail & Related papers  (2022-10-12T06:46:38Z)
• Robust and Adaptive Temporal-Difference Learning Using An Ensemble of Gaussian Processes [70.80716221080118]
  The paper takes a generative perspective on policy evaluation via temporal-difference (TD) learning. The OS-GPTD approach is developed to estimate the value function for a given policy by observing a sequence of state-reward pairs. To alleviate the limited expressiveness associated with a single fixed kernel, a weighted ensemble (E) of GP priors is employed to yield an alternative scheme.
  arXiv  Detail & Related papers  (2021-12-01T23:15:09Z)
• Consistency of mechanistic causal discovery in continuous-time using Neural ODEs [85.7910042199734]
  We consider causal discovery in continuous-time for the study of dynamical systems. We propose a causal discovery algorithm based on penalized Neural ODEs.
  arXiv  Detail & Related papers  (2021-05-06T08:48:02Z)
• Dimension Free Generalization Bounds for Non Linear Metric Learning [61.193693608166114]
  We provide uniform generalization bounds for two regimes -- the sparse regime, and a non-sparse regime. We show that by relying on a different, new property of the solutions, it is still possible to provide dimension free generalization guarantees.
  arXiv  Detail & Related papers  (2021-02-07T14:47:00Z)
• Policy Analysis using Synthetic Controls in Continuous-Time [101.35070661471124]
  Counterfactual estimation using synthetic controls is one of the most successful recent methodological developments in causal inference. We propose a continuous-time alternative that models the latent counterfactual path explicitly using the formalism of controlled differential equations.
  arXiv  Detail & Related papers  (2021-02-02T16:07:39Z)
• Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [65.44033635330604]
  We introduce a novel load forecasting method in which observed dynamics are modeled as a forced linear system. We show that its use of intrinsic linear dynamics offers a number of desirable properties in terms of interpretability and parsimony. Results are presented for a test case using load data from an electrical grid.
  arXiv  Detail & Related papers  (2020-10-08T20:25:52Z)
• PAC-Bayes Analysis Beyond the Usual Bounds [16.76187007910588]
  We focus on a learning model where the learner observes a finite set of training examples. The learned data-dependent distribution is then used to make randomized predictions.
  arXiv  Detail & Related papers  (2020-06-23T14:30:24Z)
• Learning Expected Reward for Switched Linear Control Systems: A Non-Asymptotic View [10.051309746913512]
  We show existence of invariant ergodic measure for switched linear dynamical systems. We derive non-asymptotic bounds for learning expected reward.
  arXiv  Detail & Related papers  (2020-06-15T03:13:17Z)

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.