Mahyar Fazlyab

Performance Bounds for Neural Network Estimators: Applications in Fault Detection

2021

We exploit recent results in quantifying the robustness of neural networks to input variations to construct and tune a model-based anomaly detector, where the data-driven estimator model is provided by an autoregressive neural network. In …

Towards Understanding The Semidefinite Relaxations of Truncated Least-Squares in Robust Rotation Search

2022 · arXiv (Cornell University)

The rotation search problem aims to find a 3D rotation that best aligns a given number of point pairs. To induce robustness against outliers for rotation search, prior work considers truncated least-squares (TLS), which is …