28 citations · 98 across the 47 of their papers we have counts for
56 papers
PAC-Bayesian Bounds for Learning Partially Observed Stochastic Linear Time-Invariant State-Space Systems with Inputs and Sub-Gaussian Noise
Mihaly Petreczky, Mohamad Al Ahdab, John Leth
In this paper we derive a Probably Approximately Correct (PAC)-Bayesian error bound for partially observed linear time-invariant (LTI) stochastic dynamical systems in state-space f…
Stability of input-output maps and their minimal realizations in state-linear, state-affine, LPV, and linear switched systems
Mihály Petreczky, Juan-Pablo Ortega, Florian Rossmannek +1
Stability is often assumed in learning and identification, yet it is rarely characterized directly from input--output data. We show that an input--output family admits a stable fin…
On the equivalence between functionally affine LPV state-space representations and LFT models
Mihály Petreczky, Ziad Alkhoury, Guillaume Mercère
We propose a transformation algorithm for a class of Linear Parameter-Varying (LPV) systems with functional affine dependence on parameters, where the system matrices depend affine…
A finite-sample bound for identifying partially observed linear switched systems from a single trajectory
Daniel Racz, Mihaly Petreczky, Balint Daroczy
We derive a finite-sample probabilistic bound on the parameter estimation error of a system identification algorithm for Linear Switched Systems. The algorithm estimates Markov par…
A four-bodies motorcycle dynamic model for observer design
Tychique Nzalalemba Kabwangala, Ziad Alkhoury, Jawwad Ahmed +3
Motivated by the need to predict dangerous scenarios, this article introduces a non-linear dynamic model for motorcycles consisting of four rigid bodies. Using Jourdain's principle…
A finite-sample generalization bound for stable LPV systems
Daniel Racz, Martin Gonzalez, Mihaly Petreczky +2
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 p…
Length independent generalization bounds for deep SSM architectures via Rademacher contraction and stability constraints
Dániel Rácz, Mihály Petreczky, Bálint Daróczy
Many state-of-the-art models trained on long-range sequences, for example S4, S5 or LRU, are made of sequential blocks combining State-Space Models (SSMs) with neural networks. In…
Minimal covariance realization and system identification algorithm for a class of stochastic linear switched systems with i.i.d. switching
Elie Rouphael, Manas Mejari, Mihaly Petreczky +1
In this paper, we consider stochastic realization theory of Linear Switched Systems (LSS) with i.i.d. switching. We characterize minimality of stochastic LSSs and show existence an…
Towards stochastic realization theory for Generalized Linear Switched Systems with inputs: decomposition into stochastic and deterministic components and existence and uniqueness of innovation form
Elie Rouphael, Manas Mejari, Mihaly Petreczky +1
In this paper, we study a class of stochastic Generalized Linear Switched System (GLSS), which includes subclasses of jump-Markov, piecewide-linear and Linear Parameter-Varying (LP…
PAC-Bayes Generalisation Bounds for Dynamical Systems Including Stable RNNs
Deividas Eringis, John Leth, Zheng-Hua Tan +2
In this paper, we derive a PAC-Bayes bound on the generalisation gap, in a supervised time-series setting for a special class of discrete-time non-linear dynamical systems. This cl…
Loewner functions for bilinear systems
Pauline Kergus, Ion Victor Gosea, Mihaly Petreczky
This work brings together the moment matching approach based on Loewner functions and the classical Loewner framework based on the Loewner pencil in the case of bilinear systems. N…
Theoretical Evaluation of Asymmetric Shapley Values for Root-Cause Analysis
Domokos M. Kelen, Mihály Petreczky, Péter Kersch +1
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 incorpor…
Optimization dependent generalization bound for ReLU networks based on sensitivity in the tangent bundle
Dániel Rácz, Mihály Petreczky, András Csertán +1
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 the…
PAC bounds of continuous Linear Parameter-Varying systems related to neural ODEs
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 system…
Minimal realizations of input-output behaviors by LPV state-space representations with affine dependency
Mihály Petreczky, Roland Tóth, Guillaume Mercère
The paper makes the first steps towards a behavioral theory of LPV state-space representations with an affine dependency on scheduling, by characterizing minimality of such state-s…
PAC-Bayesian bounds for learning LTI-ss systems with input from empirical loss
Deividas Eringis, John Leth, Zheng-Hua Tan +2
In this paper we derive a Probably Approxilmately Correct(PAC)-Bayesian error bound for linear time-invariant (LTI) stochastic dynamical systems with inputs. Such bounds are widesp…
Learning stability of partially observed switched linear systems
Zheming Wang, Raphaël M. Jungers, Mihály Petreczky +2
This paper deals with learning stability of partially observed switched linear systems under arbitrary switching. Such systems are widely used to describe cyber-physical systems wh…
PAC-Bayesian-Like Error Bound for a Class of Linear Time-Invariant Stochastic State-Space Models
Deividas Eringis, John Leth, Zheng-Hua Tan +2
In this paper we derive a PAC-Bayesian-Like error bound for a class of stochastic dynamical systems with inputs, namely, for linear time-invariant stochastic state-space models (st…
Noisy Learning for Neural ODEs Acts as a Robustness Locus Widening
Martin Gonzalez, Hatem Hajri, Loic Cantat +1
We investigate the problems and challenges of evaluating the robustness of Differential Equation-based (DE) networks against synthetic distribution shifts. We propose a novel and s…
Realization Theory Of Recurrent Neural ODEs Using Polynomial System Embeddings
Martin Gonzalez, Thibault Defourneau, Hatem Hajri +1
In this paper we show that neural ODE analogs of recurrent (ODE-RNN) and Long Short-Term Memory (ODE-LSTM) networks can be algorithmically embeddeded into the class of polynomial s…
On minimal LPV state-space representations in innovation form: an algebraic characterization
Elie Rouphael, Mihaly Petreczky, Lotfi Belkoura
In this paper we will propose a definition of the concept of minimal state-space representations in innovation form for LPV. We also present algebraic conditions for a stochastic L…
Application of robust control for CSR formalization and stakeholders interest
Sana Ben Abdallah, Dhafer Saidane, Mihaly Petreczky
In this paper, we propose a new definition of sustainability that includes dynamics and equity. We propose a theoretical framework that allows finding a fair equilibrium and sustai…
Explicit construction of the minimum error variance estimator for stochastic LTI state-space systems
Deividas Eringis, John Leth, Zheng-Hua Tan +2
In this short article, we showcase the derivation of the optimal (minimum error variance) estimator, when one part of the stochastic LTI system output is not measured but is able t…
Reduced-order modeling of LPV systems in the Loewner framework
Ion Victor Gosea, Mihaly Petreczky, Athanasios C. Antoulas
We propose a model reduction method for LPV systems. We consider LPV state-space representations with an affine dependence on the scheduling variables. The main idea behind the pro…