Exponential Separation between Two Learning Models and Adversarial Robustness

no code implementations • NeurIPS 2021 • Grzegorz Gluch, Ruediger Urbanke

We prove an exponential separation for the sample/query complexity between the standard PAC-learning model and a version of the Equivalence-Query-learning model.

Adversarial Robustness PAC learning +1

Spectral Clustering Oracles in Sublinear Time

no code implementations • 14 Jan 2021 • Grzegorz Gluch, Michael Kapralov, Silvio Lattanzi, Aida Mousavifar, Christian Sohler

The main technical contribution is a sublinear time oracle that provides dot product access to the spectral embedding of $G$ by estimating distributions of short random walks from vertices in $G$.

Data Structures and Algorithms