The whole is greater than its parts and the parts constitute the whole.

We give superpolynomial statistical query (SQ) lower bounds for learning twohidden-layer ReLU networks with respect to Gaussian inputs in the standard (noise-free)model.

AStackelberg game[30, 31] is a strategic interaction between two utility-maximizing players in which one player (theleader) is able to commit to a (possibly mixed) strategy before the other player (thefollower)takesanaction.

Adversarially robust classification, that has been of much recent interest, is typically formulated as follows.