20 citations · 23 across the 9 of their papers we have counts for
4 papers · 1 filter
Lipschitz Bounds for Neural Networks Using a Two-Copy Linear Fractional Transformation
Felix Biertümpfel, Bin Hu, Peter Seiler
This paper proposes a new method to bound the global Lipschitz constant of a neural network (NN). Our formulation uses a two-copy linear fractional transformation (LFT) representat…
Scalable Incremental Robustness Analysis of Neural Network Feedback Systems
Zichen Wang, Peter Seiler, Geir Dullerud +1
Semidefinite programming (SDP) certificates for feedback systems containing deep neural networks (NNs) typically scale with the total number of neurons, whereas small-gain tests ar…
Data-Driven Stability and Performance Analysis of Lurye Systems
Sahel Vahedi Noori, Peter Seiler
This paper develops data-driven conditions for certifying internal stability and induced- performance of discrete-time Lurye systems. The Lurye system is an interconnection…
Integral Quadratic Constraints for Repeated ReLU
Sahel Vahedi Noori, Bin Hu, Geir Dullerud +1
This paper presents a new dynamic integral quadratic constraint (IQC) for the repeated Rectified Linear Unit (ReLU). These dynamic IQCs can be used to analyze stability and induced…