Partial Wasserstein Covering

by   Keisuke Kawano, et al.

We consider a general task called partial Wasserstein covering with the goal of emulating a large dataset (e.g., application dataset) using a small dataset (e.g., development dataset) in terms of the empirical distribution by selecting a small subset from a candidate dataset and adding it to the small dataset. We model this task as a discrete optimization problem with partial Wasserstein divergence as an objective function. Although this problem is NP-hard, we prove that it has the submodular property, allowing us to use a greedy algorithm with a 0.63 approximation. However, the greedy algorithm is still inefficient because it requires linear programming for each objective function evaluation. To overcome this difficulty, we propose quasi-greedy algorithms for acceleration, which consist of a series of techniques such as sensitivity analysis based on strong duality and the so-called C-transform in the optimal transport field. Experimentally, we demonstrate that we can efficiently make two datasets similar in terms of partial Wasserstein divergence, including driving scene datasets.



page 9


Semi-Discrete Optimal Transport: Hardness, Regularization and Numerical Solution

Semi-discrete optimal transport problems, which evaluate the Wasserstein...

From optimal transport to generative modeling: the VEGAN cookbook

We study unsupervised generative modeling in terms of the optimal transp...

Training Wasserstein GANs without gradient penalties

We propose a stable method to train Wasserstein generative adversarial n...

The interval greedy algorithm for discrete optimization problems with interval objective function

We consider the discrete optimization problems with interval objective f...

Optimal Transport Based Seismic Inversion: Beyond Cycle Skipping

Full waveform inversion (FWI) is today a standard process for the invers...

Revisiting Fixed Support Wasserstein Barycenter: Computational Hardness and Efficient Algorithms

We study the fixed-support Wasserstein barycenter problem (FS-WBP), whic...

Bus Frequency Optimization: When Waiting Time Matters in User Satisfaction

Reorganizing bus frequency to cater for the actual travel demand can sav...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.