Abstract. This paper proposes a general approach named ExpectationMiniMax (EMM) for clustering analysis without knowing the cluster number. It describes the contrast function of Ex...
Abstract--Learning multiple related tasks from data simultaneously can improve predictive performance relative to learning these tasks independently. In this paper we propose a nov...
Jean Baptiste Faddoul, Boris Chidlovskii, Fabien T...
Learning data representations is a fundamental challenge in modeling neural processes and plays an important role in applications such as object recognition. In multi-stage Optima...
We study the problem of learning large margin halfspaces in various settings using coresets to show that coresets are a widely applicable tool for large margin learning. A large m...
We give a new model of learning motivated by smoothed analysis (Spielman and Teng, 2001). In this model, we analyze two new algorithms, for PAC-learning DNFs and agnostically learn...
Adam Tauman Kalai, Alex Samorodnitsky, Shang-Hua T...