M. Pawan Kumar
 
 

HOME

RESEARCH

PUBLICATIONS

GROUP

TALKS

TEACHING

CV

 

 

 

 

 

 

LAGRANGIAN DECOMPOSITION FOR NEURAL NETWORK VERIFICATION

A. de Palma, R. Bunel, A. Desmaison, K. Dvijotham, P. Kohli, P. Torr and M. Pawan Kumar

In Proceedings of Conference on Uncertainty in Artificial Intelligence (UAI), 2020

A fundamental component of neural network verification is the computation of bounds on the values their outputs can take. Previous methods have either used off-the-shelf solvers, discarding the problem structure, or relaxed the problem even further, making the bounds unnecessarily loose. We propose a novel approach based on Lagrangian Decomposition. Our formulation admits an efficient supergradient ascent algorithm, as well as an improved proximal algorithm. Both the algorithms offer three advantages: (i) they yield bounds that are provably at least as tight as previous dual algorithms relying on Lagrangian relaxations; (ii) they are based on operations analogous to forward/backward pass of neural networks layers and are therefore easily parallelizable, amenable to GPU implementation and able to take advantage of the convolutional structure of problems; and (iii) they allow for anytime stopping while still providing valid bounds. Empirically, we show that we obtain bounds comparable with off-the-shelf solvers in a fraction of their running time, and obtain tighter bounds in the same time as previous dual algorithms. This results in an overall speed-up when employing the bounds for formal verification.

[Paper]    [Code]