We propose a scalable end-to-end tree boosting system called XGBoost, which is used widely by data scientists to achieve state-of-the-art results on many machine learning challenges.Expand

We propose LIME, a novel explanation technique that explains the predictions of any classifier in a interpretable and faithful manner, by learning an interpretable model locally varound the prediction.Expand

We introduce the PowerGraph abstraction which exploits the internal structure of graph programs to address the challenges of computation on natural graphs in the context of existing graph-parallel abstractions.Expand

Maximum margin Markov (M3) networks incorporate both kernels, which efficiently deal with high-dimensional features, and the ability to capture correlations in structured data.Expand

We exploit submodularity to develop an efficient algorithm that scales to large problems, achieving near optimal placements, while being 700 times faster than a simple greedy algorithm.Expand

While high-level data parallel frameworks, like MapReduce, simplify the design and implementation of large-scale data processing systems, they do not naturally or efficiently support many importantâ€¦ Expand

We solve the combinatorial optimization problem of maximizing the mutual information between the chosen locations and the locations which are not selected by exploiting the submodularity of mutual information.Expand

Hamiltonian Monte Carlo sampling methods provide a mechanism for defining distant proposals with high acceptance probabilities in a Metropolis-Hastings framework, enabling more efficient exploration of the state space than standard random-walk proposals.Expand

We developed GraphLab, a new parallel abstraction which improves upon abstractions like MapReduce by compactly expressing asynchronous iterative algorithms with sparse computational dependencies.Expand