First near-linear time robust recovery guarantees for broad class of nonlinear non-monotonic Gaussian single-index models via convex basin around ground truth reachable by robust spectral initialization.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Agentic AI re-identifies 72% of individuals from simulated mobility traces by cross-referencing public web sources without human intervention.
citing papers explorer
-
Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
First near-linear time robust recovery guarantees for broad class of nonlinear non-monotonic Gaussian single-index models via convex basin around ground truth reachable by robust spectral initialization.
-
Agentic AI-Powered Re-Identification: An Emerging, Scalable Threat to Mobility Microdata Privacy
Agentic AI re-identifies 72% of individuals from simulated mobility traces by cross-referencing public web sources without human intervention.