Mihály Petreczky

Pepijn B. Cox, Roland Tóth, Mihály Petreczky

How to efficiently identify multiple-input multiple-output (MIMO) linear parameter-varying (LPV) discrete-time state-space (SS) models with affine dependence on the scheduling variable still remains an open question, as identification methods proposed in the literature suffer heavily from the curse of dimensionality and/or depend on over-restrictive approximations of the measured signal behaviors. However, obtaining an SS model of the targeted system is crucial for many LPV control synthesis methods, as these synthesis tools are almost exclusively formulated for the aforementioned representation of the system dynamics. Therefore, in this paper, we tackle the problem by combining state-of-the-art LPV input-output (IO) identification methods with an LPV-IO to LPV-SS realization scheme and a maximum likelihood refinement step. The resulting modular LPV-SS identification approach achieves statical efficiency with a relatively low computational load. The method contains the following three steps: 1) estimation of the Markov coefficient sequence of the underlying system using correlation analysis or Bayesian impulse response estimation, then 2) LPV-SS realization of the estimated coefficients by using a basis reduced Ho-Kalman method, and 3) refinement of the LPV-SS model estimate from a maximum-likelihood point of view by a gradient-based or an expectation-maximization optimization methodology. The effectiveness of the full identification scheme is demonstrated by a Monte Carlo study where our proposed method is compared to existing schemes for identifying a MIMO LPV system.

Ziad Alkhoury, Mihály Petreczky, Guillaume Mercère

It is known that in general, \emph{frozen equivalent} (Linear Parameter-Varying) LPV models, \emph{i.e.}, LPV models which have the same input-output behavior for each constant scheduling signal, might exhibit different input-output behavior for non-constant scheduling signals. In this paper, we provide an analytic error bound on the difference between the input-output behaviors of two LPV models which are frozen equivalent. This error bound turns out to be a function of both the speed of the change of the scheduling signal and the discrepancy between the coherent bases of the two LPV models. In particular, the difference between the outputs of the two models can be made arbitrarily small by choosing a scheduling signal which changes slowly enough. An illustrative example is presented to show that the choice of the scheduling signal can reduce the difference between the input-output behaviors of frozen-equivalent LPV models.

Ronald L. Westra, Mihály Petreczky, Ralf L. M. Peeters

The paper addresses the realization and identification problem or a subclass of piecewise-affine hybrid systems. The paper provides necessary and sufficient conditions for existence of a realization, a characterization of minimality, and an identification algorithm for this subclass of hybrid systems. The considered system class and the identification problem are motivated by applications in systems biology.

Domokos M. Kelen, Mihály Petreczky, Péter Kersch et al.

In this work, we examine Asymmetric Shapley Values (ASV), a variant of the popular SHAP additive local explanation method. ASV proposes a way to improve model explanations incorporating known causal relations between variables, and is also considered as a way to test for unfair discrimination in model predictions. Unexplored in previous literature, relaxing symmetry in Shapley values can have counter-intuitive consequences for model explanation. To better understand the method, we first show how local contributions correspond to global contributions of variance reduction. Using variance, we demonstrate multiple cases where ASV yields counter-intuitive attributions, arguably producing incorrect results for root-cause analysis. Second, we identify generalized additive models (GAM) as a restricted class for which ASV exhibits desirable properties. We support our arguments by proving multiple theoretical results about the method. Finally, we demonstrate the use of asymmetric attributions on multiple real-world datasets, comparing the results with and without restricted model families using gradient boosting and deep learning models.

Dániel Rácz, Mihály Petreczky, András Csertán et al.

Recent advances in deep learning have given us some very promising results on the generalization ability of deep neural networks, however literature still lacks a comprehensive theory explaining why heavily over-parametrized models are able to generalize well while fitting the training data. In this paper we propose a PAC type bound on the generalization error of feedforward ReLU networks via estimating the Rademacher complexity of the set of networks available from an initial parameter vector via gradient descent. The key idea is to bound the sensitivity of the network's gradient to perturbation of the input data along the optimization trajectory. The obtained bound does not explicitly depend on the depth of the network. Our results are experimentally verified on the MNIST and CIFAR-10 datasets.

Dániel Rácz, Mihály Petreczky, Bálint Daróczy

We consider the problem of learning Neural Ordinary Differential Equations (neural ODEs) within the context of Linear Parameter-Varying (LPV) systems in continuous-time. LPV systems contain bilinear systems which are known to be universal approximators for non-linear systems. Moreover, a large class of neural ODEs can be embedded into LPV systems. As our main contribution we provide Probably Approximately Correct (PAC) bounds under stability for LPV systems related to neural ODEs. The resulting bounds have the advantage that they do not depend on the integration interval.

Ziad Alkhoury, Mihály Petreczky, Guillaume Mercère

In this paper, we introduce and study important properties of the transformation of Affine Linear Parameter-Varying (ALPV) state-space representations into Linear Fractional Representations (LFR). More precisely, we show that $(i)$ state minimal ALPV representations yield minimal LFRs, and vice versa, $(ii)$ the input-output behavior of the ALPV represention determines uniquely the input-output behavior of the resulting LFR, $(iii)$ structurally identifiable ALPVs yield structurally identifiable LFRs, and vice versa. We then characterize LFR models which correspond to equivalent ALPV models based on their input-output maps. As illustrated all along the paper, these results have important consequences for identification and control of systems described by LFRs.