AI Paper Atlas

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

A Robust Optimisation Perspective on Counterexample-Guided Repair of Neural Networks

David Boetius, Stefan Leue, Tobias Sutter

ICML 2023 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 0 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
Solve the linear-regression repair problem directly as a quadratic programRMI second-stage linear regression · RMI second-stage linear regression, ε = 100success rate: 58% -> 72 %Improved
Solve the linear-regression repair problem directly as a quadratic programRMI second-stage linear regression · RMI second-stage linear regression, ε = 150success rate: 94% -> 97 %Improved
Use an early-exit verifier instead of an optimal verifierCounterexample-guided repair · MNIST and ACAS XuruntimeImproved
Use an optimal verifier instead of an early-exit verifierCounterexample-guided repair · MNIST and ACAS Xurepair stepsImproved
Use an early-exit verifier instead of an optimal verifierCounterexample-guided repair · CollisionDetection and RMI first-stage networksruntimeNo clear effect
Use BIM falsification to search for counterexamples before invoking the verifierMNIST repair · MNISTruntimeImproved

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