In recent years, deep learning has become a staple solution to different tasks, such as computer vision,bio-informatics,speechrecognition,andmanymore.

For deterministic feedback, we additionally present a gap-independent algorithm that identifies a Condorcet winning team withinO(nklog(k)+k5)duels.

Swap regret, a generic performance measure of online decision-making algorithms, plays an important role in the theory of repeated games, along with a closeconnection tocorrelated equilibria instrategicgames.

Human communication has a multi-modal and multi-affect nature.

We study the problem of agnostically learning homogeneous halfspaces in the distribution-specific PAC model. For a broad family of structured distributions, including log-concave distributions, we show that non-convex SGD efficiently convergestoasolution withmisclassification errorO(opt)+,whereoptisthe misclassification error of the best-fitting halfspace.