AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Blending Neural Control Density Functions for Stabilization and Safety

Sahil Chaudhary, Chaitanya Murti, Chiranjib Bhattacharyya

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add the exponential parametrization of density and control (Eq. 18) instead of a/b and c/a ratio parametrization (ablation)NCDF on system (33) · Prajna et al. system (33) control synthesisstabilizationImproved
blend learned NCDF controllers with the SoS controller of Prajna et al.NCDF controllers · Prajna et al. systems (33)-(35)region of attractionImproved
use neural density function instead of neural Lyapunov functionstability certification · system (24) with four equilibriastability certificationImproved
use NCDF instead of neural Lyapunov functionstability certification · system (32) with two equilibriastability certificationImproved
use NCDF instead of Yang et al. 2024 for certified RoANCDF · Inverted pendulumcertified region of attractionImproved
use NCDF instead of Yang et al. 2024 for certified RoANCDF · Path trackingcertified region of attractionNo clear effect
call the falsifier every 500 iterations instead of every 100 (ablation)NCDF on inverted pendulum · Inverted Pendulum falsification frequencytotal learning time: 3m 23s -> 23sImproved
call the falsifier every 250 iterations instead of every 100 (ablation)NCDF on inverted pendulum · Inverted Pendulum falsification frequencytotal learning time: 3m 23s -> 3m 53sHurt
call the falsifier every 750 iterations instead of every 500 (ablation)NCDF on inverted pendulum · Inverted Pendulum falsification frequencytotal learning time: 23s -> 22.4sNo clear effect

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