3 papers
stat.ML2016
Horizontally Scalable Submodular Maximization
Mario Lucic, Olivier Bachem, Morteza Zadimoghaddam +1
A variety of large-scale machine learning problems can be cast as instances of constrained submodular maximization. Existing approaches for distributed submodular maximization have…
stat.ML2016
Tradeoffs for Space, Time, Data and Risk in Unsupervised Learning
Mario Lucic, Mesrob I. Ohannessian, Amin Karbasi +1
Faced with massive data, is it possible to trade off (statistical) risk, and (computational) space and time? This challenge lies at the heart of large-scale machine learning. Using…
stat.ML2016
Linear-time Outlier Detection via Sensitivity
Mario Lucic, Olivier Bachem, Andreas Krause
Outliers are ubiquitous in modern data sets. Distance-based techniques are a popular non-parametric approach to outlier detection as they require no prior assumptions on the data g…