Timezone: »

 
Poster
argmax centroid
Chengyue Gong · Mao Ye · Qiang Liu

Tue Dec 07 04:30 PM -- 06:00 PM (PST) @
in Poster Session 2 »

We propose a general method to construct centroid approximation for the distribution of maximum points of a random function (a.k.a. argmax distribution), which finds broad applications in machine learning. Our method optimizes a set of centroid points to compactly approximate the argmax distribution with a simple objective function, without explicitly drawing exact samples from the argmax distribution. Theoretically, the argmax centroid method can be shown to minimize a surrogate of Wasserstein distance between the ground-truth argmax distribution and the centroid approximation under proper conditions. We demonstrate the applicability and effectiveness of our method on a variety of real-world multi-task learning applications, including few-shot image classification, personalized dialogue systems and multi-target domain adaptation.

Keywords: Machine Learning · Vision · Meta Learning · Domain Adaptation · Few Shot Learning

Author Information

Chengyue Gong (Peking University)
Mao Ye (The University of Texas at Austin)
Qiang Liu (Dartmouth College)

More from the Same Authors