BoundLab Documentation#

BoundLab is a framework for building neural network verification tools using symbolic expressions and bound propagation.

Mental model: represent relaxed abstract values as Expr, transform them (for example with zono.interpret), then apply dual-norm concretization (ub, lb, ublb).

This documentation is organized into three learning paths:

  • Getting Started: install BoundLab and run your first bound computation.

  • User Guide: understand the expression system, propagation APIs, and interpreter workflow.

  • Examples: end-to-end patterns you can adapt to your own models.

Getting Started

Install BoundLab and run your first verification script.

Getting Started
User Guide

Core concepts, supported operations, and practical workflow guidance.

User Guide
Examples

Task-focused examples from manual expression building to model interpretation.

Examples
API Reference

Autogenerated API docs for all public modules, classes, and functions.

API Reference