activity
20182022
most citedRiemannian adaptive stochastic gradient algorithms on matrix manifolds

23 citations · 36 across the 7 of their papers we have counts for

collaborators

13 papers

cs.LG20221 cited

On the Convergence of Semi-Relaxed Sinkhorn with Marginal Constraint and OT Distance Gaps

Takumi Fukunaga, Hiroyuki Kasai

This paper presents consideration of the Semi-Relaxed Sinkhorn (SR-Sinkhorn) algorithm for the semi-relaxed optimal transport (SROT) problem, which relaxes one marginal constraint…

cs.LG20227 cited

Block-coordinate Frank-Wolfe algorithm and convergence analysis for semi-relaxed optimal transport problem

Takumi Fukunaga, Hiroyuki Kasai

The optimal transport (OT) problem has been used widely for machine learning. It is necessary for computation of an OT problem to solve linear programming with tight mass-conservat…

cs.LG20213 cited

Fast block-coordinate Frank-Wolfe algorithm for semi-relaxed optimal transport

Takumi Fukunaga, Hiroyuki Kasai

Optimal transport (OT), which provides a distance between two probability distributions by considering their spatial locations, has been applied to widely diverse applications. Com…

cs.LG2021

Manifold optimization for non-linear optimal transport problems

Bamdev Mishra, N T V Satyadev, Hiroyuki Kasai +1

Optimal transport (OT) has recently found widespread interest in machine learning. It allows to define novel distances between probability measures, which have shown promise in sev…

cs.LG2020

LCS Graph Kernel Based on Wasserstein Distance in Longest Common Subsequence Metric Space

Jianming Huang, Zhongxi Fang, Hiroyuki Kasai

For graph learning tasks, many existing methods utilize a message-passing mechanism where vertex features are updated iteratively by aggregation of neighbor information. This strat…

cs.LG20202 cited

Wasserstein k-means with sparse simplex projection

Takumi Fukunaga, Hiroyuki Kasai

This paper presents a proposal of a faster Wasserstein -means algorithm for histogram data by reducing Wasserstein distance computations and exploiting sparse simplex projection…