We propose a non-iterative method that enforces the following ideas during training.

Insuch situations, weallowthealgorithm toreturn asmall listofcandidates such that one of the candidates is close to the true parameter.

Community detection is an essential tool for unsupervised data exploration and revealing theorganisational structure ofnetworkedsystems. Withalong history innetwork science, community detection typically relies on objectivefunctions, optimised with custom-tailored search algorithms, but often without leveraging recentadvancesindeeplearning.

However, the theoretical convergence of ANIL has not been studied yet.

Learning to navigate to an image-specified goal is an important but challenging task for autonomous systems. The agent is required to reason the goal location from where a picture is shot.

Our ideas also can be applied to the more general setting that the objective function only satisfies PL condition for one variable.