SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.00415 · 2019

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, we focus on mixture distributions that arise naturally in several application domains where the data contains different sub-populations. For mixture distributions, established distance measures such as the Wasserstein distance do not take into account imbalanced mixture proportions. Thus, even if two mixture distributions have identical mixture components but different mixture proportions, the Wasserstein distance between them will be large. This often leads to undesired results in distance-based learning methods for mixture distributions. In this paper, we resolve this issue by introducing the Normalized Wasserstein measure. The key idea is to introduce mixture proportions as optimization variables, effectively normalizing mixture proportions in the Wasserstein formulation. Using the proposed normalized Wasserstein measure leads to significant performance gains for mixture distributions with imbalanced mixture proportions compared to the vanilla Wasserstein distance. We demonstrate the effectiveness of the proposed measure in GANs, domain adaptation and adversarial clustering in several benchmark datasets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1902.00415")
get_code_for_paper("1902.00415")
have("1902.00415")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1902.00415.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1902.00415.svg)](https://syntology.ai/paper/1902.00415)

Connect an agent — have() is free.