AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Provable State Estimation with Recurrent Models

Vincent Andrieu, Pauline Bernard, Lucas Brivadis, Laurent Praly, Christian Wolf

NeurIPS 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Stable contractive dynamics · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Analyzes recurrent neural networks as time discretizations of Neural ODEs through the lens of nonlinear observer theory to obtain formal convergence and robustness guarantees for state estimation.

Problem

Recurrent models used for estimating the state of dynamical systems from observations lack formal guarantees on convergence and robustness.

Approach

Frames RNNs as time-discretized continuous latent dynamical systems (Neural ODEs) and applies nonlinear observer theory to derive provable convergence and robustness properties for state estimation.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enforce contraction in the GRU (Contracting GRU with spectral normalization) instead of a vanilla GRU2-layer GRU pose-correction model · Real mobile-robot pose correction (accuracy vs relative error)pose accuracyImproved
enforce contraction, measured as variability over 5 training runsGRU · Real mobile-robot pose correctiontraining stability across seedsImproved
train an unconstrained GRU with no contraction constraintGRU · Real mobile-robot pose correctionstate-distance contractionImproved
increase latent gain kappa beyond about 2 (ablation)RNN-MLP observer · Simulated nonlinear oscillator, every decoder widthsteady-state RMS errorHurt
increase latent gain kappa from 0.5 up to about 2 (ablation)RNN-MLP observer · Simulated nonlinear oscillatorsteady-state RMS errorImproved
widen the MLP decoder (ablation)RNN-MLP observer · Simulated nonlinear oscillatorabsolute errorImproved
raise gain kappa to 20 with widest decoder (4096) (ablation)RNN-MLP observer · Simulated nonlinear oscillator, reconstruction error over timetransient speed and steady-state errorMixed

Experimental setup

Builds on: Neural ODE

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy