In this work we develop a theory of hierarchical clustering for graphs. Our modeling assumption is that graphs are sampled from a graphon, which is a powerful and general model for generating graphs and analyzing large networks. Graphons are a far richer class of graph models than stochastic blockmodels, the primary setting for recent progress in the statistical theory of graph clustering. We define what it means for an algorithm to produce the "correct" clustering, give sufficient conditions in which a method is statistically consistent, and provide an explicit algorithm satisfying these properties.

The most commonly studied and utilised version considers only a diagonal matrix proximal term.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

We study the potential of a "blind attacker" to provably limit a learner's performance by data injection attack without observing the learner's

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

Most methods for this so-called "Bayesian optimization" only allow sequential exploration of the parameter space.

Moreover, we find two additional surprising properties of CNNs: they are less susceptible to overfitting than their LN counterparts when trained on small amounts of data, and generalize better when tested on stimuli drawn from a different distribution (e.g. between natural scenes and white noise). An examination of the learned CNNs reveals several properties. First, a richer set of feature maps is necessary for predicting the responses to natural scenes compared to white noise.

We report state-of-the-art results in predicting the locations of human gaze fixations, even though our model is trained only on image-level labels without object location annotations.