Entity · technique

Extended Kalman Filter

techniqueactiveextended-kalman-filter-1b213dba·1 events·first seen Jun 1, 2026

Aliases: Extended Kalman Filter

Co-occurring entities

Dynamic-Probabilistic Consistency Gap Lorenz-96 Dynamical Systems Reconstruction DSR Foundation Model KAFFEE

More like this (12)

Kernel Density Estimator (KDE)Laplace Kernel EmbedFilter KL-regularized RL Variance-Calibrated Modulation differentiable dynamics sensor calibration Last-Mile Forecasting Framework FeedForward submodule Gaussian kernel smoothing reverse KL divergence Behavioral Trajectory Tracking Framework Toward Calibrated Mixture-of-Experts Under Distribution Shift

Recent events (1)

5arXiv · cs.LG·Jun 1, 2026·source ↗

KAFFEE: Addressing the Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling

This paper identifies a 'dynamic-probabilistic consistency (DPC) gap' in dynamical systems reconstruction (DSR), where optimizing finite-horizon probabilistic objectives can degrade learned dynamics or decouple predictive uncertainty from local tangent dynamics. Three failure mechanisms are isolated: core collapse, noise masking, and blind uncertainty. The authors propose KAFFEE, a differentiable extended Kalman filter-based training framework that evaluates likelihood on local predictive residuals while transporting covariance through learned Jacobians, reducing these failure modes on stochastic hyperchaotic Lorenz-96 and across 13 chaotic systems when adapting a DSR foundation model.

Evaluation and Benchmarking AI Safety Research Dynamic-Probabilistic Consistency Gap Extended Kalman Filter Lorenz-96 +3 more