AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions

Rayan Mazouz, Karan Muvvala, Akash Ratheesh Babu, Luca Laurenti, Morteza Lahijanian

NeurIPS 2022 · Learning theory and algorithms › Combinatorial and search optimization · approach: Constrained neural network optimization · 8 citations (OpenAlex)

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
use linear bounds instead of interval bounds for NN relaxation (ablation)barrier certificate · Cartpole 1x[128], |Q|=960safety probability Ps: 0.00 -> 0.375Improved
use linear bounds instead of interval bounds for NN relaxation (ablation)barrier certificate · Pendulum 2x[64], |Q|=480safety probability Ps: 0.802 -> 0.919Improved
use linear bounds instead of interval bounds for NN relaxation (ablation)barrier certificate · Husky 4D 2x[256], |Q|=4800safety probability Ps: 0.062 -> 0.384Improved
refine partition from 960 to 3840 regions (ablation)barrier certificate (linear bounds) · Cartpole 1x[128]safety probability Ps: 0.375 -> 0.599Improved
refine partition from 1800 to 4800 regions (ablation)barrier certificate (linear bounds) · Husky 4D 2x[256]safety probability Ps: 0.010 -> 0.384Improved
add minimally-invasive controllerbarrier certificate (linear bounds) · Husky 4D 2x[256], |Q|=1800safety probability Ps: 0.010 -> 0.800Improved
add minimally-invasive controllerbarrier certificate (linear bounds) · Husky 5D 1x[512], |Q|=432safety probability Ps: 0.00 -> 0.949Improved
add minimally-invasive controllerbarrier certificate (linear bounds) · Cartpole 1x[128], |Q|=960safety probability Ps: 0.375 -> 0.998Improved
use linear bounds instead of interval bounds for control synthesis (ablation)controller · Husky 5D 1x[512], |Q|=432safety probability Ps: 0.750 -> 0.949Improved
refine partition from 120 to 480 regions (ablation)interval-bound certificate · Pendulum 1x[64]safety probability Ps: 0.468 -> 0.854Improved

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