8 citations · 9 across the 4 of their papers we have counts for
4 papers
Stability Guarantees for Feature Attributions with Multiplicative Smoothing
Anton Xue, Rajeev Alur, Eric Wong
Explanation methods for machine learning models tend not to provide any formal guarantees and may not reflect the underlying decision-making process. In this work, we analyze stabi…
Chordal Sparsity for SDP-based Neural Network Verification
Anton Xue, Lars Lindemann, Rajeev Alur
Neural networks are central to many emerging technologies, but verifying their correctness remains a major challenge. It is known that network outputs can be sensitive and fragile…
Chordal Sparsity for Lipschitz Constant Estimation of Deep Neural Networks
Anton Xue, Lars Lindemann, Alexander Robey +3
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data. As ca…
Data-Driven System Level Synthesis
Anton Xue, Nikolai Matni
We establish data-driven versions of the System Level Synthesis (SLS) parameterization of achievable closed-loop system responses for a linear-time-invariant system over a finite-h…