Abstract Stochastic Gradient Descent (SGD) is a popular algorithm that can achieve state-of-
the-art performance on a variety of machine learning tasks. Several researchers have …

Tracking new topics, ideas, and" memes" across the Web has been an issue of considerable
interest. Recent work has developed methods for tracking topic shifts over long time scales …

Discrete optimization problems are everywhere, from traditional operations research
planning (scheduling, facility location and network design); to computer science databases; …

Weakly supervised semantic instance segmentation with only image-level supervision,
instead of relying on expensive pixel-wise masks or bounding box annotations, is an …

On the Unique Games Conjecture Page 1 On the Unique Games Conjecture Subhash Khot
Courant Institute of Mathematical Sciences, NYU ∗ Abstract This article surveys recently …

In a traditional classification problem, we wish to assign one of k labels (or classes) to each
of n objects, in a way that is consistent with some observed data that we have about the …

We consider the problem of clustering a collection of elements based on pairwise judgments
of similarity and dissimilarity. Bansal et al.(in: Proceedings of 43rd FOCS, 2002, pp. 238 …

Szeliski et al. published an influential study in 2006 on energy minimization methods for
Markov random fields. This study provided valuable insights in choosing the best …

Modern graph or network datasets often contain rich structure that goes beyond simple
pairwise connections between nodes. This calls for complex representations that can …

We describe a convex relaxation for a family of problems of minimal perimeter partitions. The
minimization of the relaxed problem can be tackled numerically: we describe an algorithm …