Automated Formal Synthesis of Lyapunov Neural Networks

03/19/2020
by   Alessandro Abate, et al.
0

We propose an automated and sound technique to synthesize provably correct Lyapunov functions. We exploit a counterexample-guided approach composed of two parts: a learner provides candidate Lyapunov functions, and a verifier either guarantees the correctness of the candidate or offers counterexamples, which are used incrementally to further guide the synthesis of Lyapunov functions. Whilst the verifier employs a formal SMT solver, thus ensuring the overall soundness of the procedure, a neural network is used to learn and synthesize candidates over a domain of interest. Our approach flexibly supports neural networks of arbitrary size and depth, thus displaying interesting learning capabilities. In particular, we test our methodology over non-linear models that do not admit global polynomial Lyapunov functions, and compare the results against a cognate δ-complete approach, and against an approach based on convex (SOS) optimization. The proposed technique outperforms these alternatives, synthesizing Lyapunov functions faster and over wider spatial domains.

READ FULL TEXT

Authors

page 1

page 2

page 3

page 4

07/21/2020

Automated and Sound Synthesis of Lyapunov Functions with SMT Solvers

In this paper we employ SMT solvers to soundly synthesise Lyapunov funct...
07/07/2020

Automated Formal Synthesis of Neural Barrier Certificates for Dynamical Models

We introduce an automated, formal, counterexample-based approach to synt...
07/21/2014

Are There Good Mistakes? A Theoretical Analysis of CEGIS

Counterexample-guided inductive synthesis CEGIS is used to synthesize pr...
01/25/2020

CounterExample Guided Neural Synthesis

Program synthesis is the generation of a program from a specification. C...
11/05/2020

An SMT-Based Approach for Verifying Binarized Neural Networks

Deep learning has emerged as an effective approach for creating modern s...
10/07/2020

Global Optimization of Objective Functions Represented by ReLU Networks

Neural networks (NN) learn complex non-convex functions, making them des...
02/12/2021

Data-Driven Synthesis of Provably Sound Side Channel Analyses

We propose a data-driven method for synthesizing a static analyzer to de...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.