This paper presents a new lower bound for the discrete strategy improvement algorithm for solving parity games due to V¨oge and Jurdzi´nski. First, we informally show which stru...
We demonstrate how to leverage a system’s capability for allto-all communication to achieve an exponential speed-up of local algorithms despite bandwidth and memory restrictions...
The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perceptron le...
Abstract. Given a family of subsets of an n-element universe, the kcover problem asks whether there are k sets in the family whose union contains the universe; in the k-packing pro...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...