Modern neural networks have the capacity to overfit noisy labels frequently found in real-
world datasets. Although great progress has been made, existing techniques are very …

We connect high-dimensional subset selection and submodular maximization. Our results
extend the work of Das and Kempe [In ICML (2011) 1057–1064] from the setting of linear …

In many machine learning applications, it is important to explain the predictions of a black-
box classifier. For example, why does a deep neural network assign an image to a particular …

Evolutionary algorithms (EAs) are a kind of nature-inspired general-purpose optimization
algorithm, and have shown empirically good performance in solving various real-word …

We propose and analyze batch greedy heuristics for cardinality constrained maximization of
non-submodular non-decreasing set functions. We consider the standard greedy paradigm …

We connect high-dimensional subset selection and submodular maximization. Our results
extend the work of Das and Kempe (2011) from the setting of linear regression to arbitrary …

As evolutionary algorithms (EAs) are general-purpose optimization algorithms, recent
theoretical studies have tried to analyze their performance for solving general problem …

The paper provides statistical theory and intuition for personalized PageRank (called 'PPR'):
a popular technique that samples a small community from a massive network. We study a …

Submodular maximization with a cardinality constraint can model various problems, and
those problems are often very large in practice. For the case where objective functions are …

The subspace selection problem seeks a subspace that maximizes an objective function
under some constraint. This problem includes several important machine learning problems …