28 citations · 98 across the 47 of their papers we have counts for
10 papers · 1 filter
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…
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 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…
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…
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…
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…
Improved PAC-Bayesian Bounds for Linear Regression
Vera Shalaeva, Alireza Fakhrizadeh Esfahani, Pascal Germain +1
In this paper, we improve the PAC-Bayesian error bound for linear regression derived in Germain et al. [10]. The improvements are twofold. First, the proposed error bound is tighte…