We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...
Abstract. Modern termination provers rely on a safety checker to construct disjunctively well-founded transition invariants. This safety check is known to be the bottleneck of the ...
Daniel Kroening, Natasha Sharygina, Aliaksei Tsito...
We present a theoretical analysis of supervised ranking, providing necessary and sufficient conditions for the asymptotic consistency of algorithms based on minimizing a surrogate...
While many visualization tools exist that offer sophisticated functions for charting complex data, they still expect users to possess a high degree of expertise in wielding the to...
Yiwen Sun, Jason Leigh, Andrew E. Johnson, Sangyoo...
Abstract. There is currently a large interest in probabilistic logical models. A popular algorithm for approximate probabilistic inference with such models is Gibbs sampling. From ...