We study the problem of learning large margin halfspaces in various settings using coresets to show that coresets are a widely applicable tool for large margin learning. A large m...
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
It is usually assumed that the kind of noise existing in annotated data is random classification noise. Yet there is evidence that differences between annotators are not always ra...
We present a tamper-proof and lightweight challenge-response authentication scheme based on 2-level noisy Physically Unclonable Functions (PUF). We present a security reduction, w...
We study the phenomenon of cognitive learning from an algorithmic standpoint. How does the brain effectively learn concepts from a small number of examples despite the fact that e...