In this paper we adapt the nearest neighbour rule to the contextual bandit problem.

We represent these edges as a collection of parametric curves(i.e., lines, circles, and B-splines).

It has several appealing benefits that prior arts donothave.

OpenAI President Greg Brockman and venture capitalist Ben Horowitz are funding a political group to support lawmakers who support AI regulatory frameworks.

For a range of activation functions, including ReLUs, we establish superpolynomial Statistical Query (SQ) lower bounds for this learning problem.