This work explores the application of solver-level warmstarting for neural network verification to exploit information from previous solutions, using a pipeline that is generalisable and potentially adaptable to state-of-the-art verifiers.
Abstract
Neural network verification has become a key tool for providing formal guarantees on the behaviour of neural networks. However, many verification problems remain computationally intractable in the worst case: even for common adversarial robustness specifications, verification is NP-complete. Here, we explore the application of solver-level warmstarting for neural network verification to exploit information from previous solutions. We study the effect on running time as several properties are modified, including perturbation radii, input data and the networks themselves, using a pipeline that is generalisable and potentially adaptable to state-of-the-art verifiers. Our results show that warmstarting can significantly reduce verification time in most cases. Moreover, warmstarting enables the successful verification of instances that could not be solved from scratch within the given time limit.
This tutorial explores Marabou, a tool for formally verifying deep neural networks (DNNs), and presents the theoretical foundations of DNN verification and an overview of Marabou’s core algorithms.
Formal verification can play a key role in ensuring the reliability of Deep Neural Networks (DNNs) deployed in safety-critical systems. Modern DNN verifiers employ a branch-and-bound framework, which alternates between branching (splitting into smaller subproblems) and bounding (pruning subproblems) to efficiently expl...
ZonoGpt, an abstract domain for verifying large transformers that maintains a space complexity independent of network depth, is introduced, an abstract domain for verifying large transformers that maintains a space complexity independent of network depth.
This work aims to formally verify safety properties of discrete-time unknown systems by synthesizing extreme learning machine (ELM)-based barrier certificates by minimizing the Lipschitz constant of the candidate barrier by presenting a grid-based sampling technique to formally verify its validity using the minimum num...
NNV3 is presented, the latest version of the Neural Network Verification tool, a MATLAB framework for formal verification of deep learning models and learning-enabled cyber-physical systems, demonstrating NNV's maturation into a comprehensive, robust, and accessible verification tool for a diverse range of AI systems.
Anne M. Tumlin, Samuel Sasaki, Ben Wooding et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026