
DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting
Analyzing the worstcase performance of deep neural networks against inp...
read it

On Centralized and Distributed Mirror Descent: Exponential Convergence Analysis Using Quadratic Constraints
Mirror descent (MD) is a powerful firstorder optimization technique tha...
read it

Performance Bounds for Neural Network Estimators: Applications in Fault Detection
We exploit recent results in quantifying the robustness of neural networ...
read it

Certifying Incremental Quadratic Constraints for Neural Networks
Abstracting neural networks with constraints they impose on their inputs...
read it

Enforcing robust control guarantees within neural network policies
When designing controllers for safetycritical systems, practitioners of...
read it

Stability Analysis of Complementarity Systems with Neural Network Controllers
Complementarity problems, a class of mathematical optimization problems ...
read it

Robust Deep Learning as Optimal Control: Insights and Convergence Guarantees
The fragility of deep neural networks to adversariallychosen inputs has...
read it

ReachSDP: Reachability Analysis of ClosedLoop Systems with Neural Network Controllers via Semidefinite Programming
There has been an increasing interest in using neural networks in closed...
read it

Probabilistic Verification and Reachability Analysis of Neural Networks via Semidefinite Programming
Quantifying the robustness of neural networks or verifying their safety ...
read it

Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networks
Tight estimation of the Lipschitz constant for deep neural networks (DNN...
read it

Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programming
Analyzing the robustness of neural networks against normbounded uncerta...
read it
Mahyar Fazlyab
is this you? claim profile