April 15th, 2014, 4:00pm CSE 691 (The Gates Commons) Sanjeev Arora, Department of Computer Science, Princeton. Overcoming Intractability in Unsupervised Learning Abstract: Unsupervised learning – i.e., learning with unlabeled data – is increasingly important given today’s data deluge. Most natural problems in this domain – e.g. for models such as mixture models, HMMs, graphical models, topic models and sparse […]
↧