Poster
On Scalable and Efficient Computation of Large Scale Optimal Transport
Yujia Xie · Minshuo Chen · Haoming Jiang · Tuo Zhao · Hongyuan Zha

Thu Jun 13th 06:30 -- 09:00 PM @ Pacific Ballroom #10

Optimal Transport (OT) naturally arises in many machine learning applications, yet the heavy computational burden limits its wide-spread uses. To address the scalability issue, we propose an implicit generative learning-based framework called SPOT (Scalable Push-forward of Optimal Transport). Specifically, we approximate the optimal transport plan by a pushforward of a reference distribution, and cast the optimal transport problem into a minimax problem. We then can solve OT problems efficiently using primal dual stochastic gradient-type algorithms. We also show that we can recover the density of the optimal transport plan using neural ordinary differential equations. Numerical experiments on both synthetic and real datasets illustrate that SPOT is robust and has favorable convergence behavior. SPOT also allows us to efficiently sample from the optimal transport plan, which benefits downstream applications such as domain adaptation.

Author Information

Yujia Xie (Georgia Institute of Technology)
Minshuo Chen (Georgia Tech)
Haoming Jiang (Georgia Tech)
Tuo Zhao (Georgia Institute of Technology)
Hongyuan Zha (Georgia Institute of Technology)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors