We give the first representation-independent hardness result for agnostically learning halfspaces with respect to the Gaussian distribution. We reduce from the problem of learning sparse parities with noise with respect to the uniform distribution on the hypercube (sparse LPN), a notoriously hard problem in computer science and show that ... more >>>

We prove a version of "Reversed Newman Theorem" in context of information complexity: every private-coin communication protocol with information complexity $I$ and communication complexity $C$ can be replaced by public-coin protocol with the same behavior so that it's information complexity does not exceed $O\left(\sqrt{IC}\right)$. This result holds for unbounded-round communication ... more >>>

For a Boolean function $f,$ let $D(f)$ denote its deterministic decision tree complexity, i.e., minimum number of (adaptive) queries required in worst case in order to determine $f.$ In a classic paper,
Rivest and Vuillemin \cite{rv} show that any non-constant monotone property $\mathcal{P} : \{0, 1\}^{n \choose 2} \to ... more >>>