Timezone: »

On Herding and the Perceptron Cycling Theorem
Andrew E Gelfand · Yutian Chen · Laurens van der Maaten · Max Welling

Wed Dec 08 12:00 AM -- 12:00 AM (PST) @

The paper develops a connection between traditional perceptron algorithms and recently introduced herding algorithms. It is shown that both algorithms can be viewed as an application of the perceptron cycling theorem. This connection strengthens some herding results and suggests new (supervised) herding algorithms that, like CRFs or discriminative RBMs, make predictions by conditioning on the input attributes. We develop and investigate variants of conditional herding, and show that conditional herding leads to practical algorithms that perform better than or on par with related classifiers such as the voted perceptron and the discriminative RBM.

Author Information

Andrew E Gelfand (University of California, Irvine)
Yutian Chen (Google DeepMind)
Laurens van der Maaten (Facebook AI Research)
Max Welling (Microsoft Research AI4Science / University of Amsterdam)

More from the Same Authors