We consider distributed convex optimization problems in the regime when the communication between the server and the workers is expensive in both uplink and downlink directions.

We consider the problem of regret minimization in non-parametric stochastic bandits. When the rewards are known to be bounded from above, there exists asymptotically optimal algorithms, with asymptotic regret depending on an infi-mum of Kullback-Leibler divergences (KL).

Internal measures that are used to assess the quality of a clustering usually take into account intra-group and/or inter-group criteria.

In essence, these tools exploit the stability and spherical symmetry of Gaussian distributions.

Machine learning research has long focused on models rather than datasets, and prominent datasets are used for common ML tasks without regard to the breadth, difficulty, and faithfulness of the underlying problems. Neglecting the fundamental importance of data has given rise to inaccuracy, bias, and fragility in real-world applications, and research is hindered by saturation across existing dataset benchmarks.

GAN framework to generate synthetic glucose traces.