LATEST NEWS


2024-01-26
News AO Admission to English-based Program Entering in September 2024 NEW!

2023-10-26
Paper arXiv paper "Anchor Space OT: Accelerating Batch Processing of Multiple OTs"

2023-07-01
Paper arXiv paper "Safe Screening for Unbalanced Optimal Transport"

2022-11-22
Paper AAAI-23 "Wasserstein Graph Distance with L1 TED between WL Subtrees"

2022-07-18
News NMFLibrary 2.0 Release

2022-07-12
Paper arXiv paper "Wasserstein Graph Distance with L1 TED between WL Subtrees"

2022-05-31
Paper arXiv paper "On the convergence of semi-relaxed Sinkhorn algorithm"

2022-05-17
Paper EUSIPCO2022 "Auto-weighted sequential Wasserstein distance"

2022-05-10
News New members for FY2022 (3rd term)

2022-01-25
Paper ICASSP2022 "Block-coordinate Frank-Wolfe algorithm for semi-relaxed OT"

2021-10-22
News Book chapter in "Tensors for Data Processing (1st Edition)"

2021-08-05
Paper Journal Signal Processing "LCS graph kernel based on Wasserstein distance"

2021-04-21
Event New members for FY2021 (2nd term)

2021-03-11
Paper arXiv paper "Block-coordinate Frank-Wolfe for semi-relaxed optimal transport"

2021-03-03
Paper arXiv paper and tool "Manifold optimization for optimal transport"

2021-01-30
Paper ICASSP2021 "Graph embedding using multi-layer adjacent point merging model"

2020-12-11
Presen OPT2020 "Riemannian optimization on the simplex of positive definite matrices"

2020-10-12
Paper ICPR2020 "Wasserstein k-means with sparse simplex projection"

2020-06-03
Paper EUSIPCO2020 "Consistency- and inconsistency-aware graph-based multi-view clustering"

2020-04-26
Event New members for FY2020 (First term)

2020-04-15
Event Article for Close Up

2020-01-25
Paper ICASSP2020 three papers

2019-09-21
News Laboratory Open at Waseda University

2019-06-15
Presen Presentation at ICML2019

2019-02-07
Paper R-SVRG accepted to SIAM Journal on Optimization (SIOPT)

2018-12-25
Paper Grassmann Manifold Distributed Opt. accepted to Machine Learning

2018-12-17
Presen Presentation at NeurIPS2018

Machine learning, optimization, and signal processing

We are dedicated to machine learning, optimization, and signal processing, and their theories, algorithms, and applications for small- and large-scale data. Specifically, we address learning algorithms and models, optimization algorithms,  linear & non-linear optimization problems, convex & non-convex optimization problems, classification and clustering problems, distance and space learning problems, structure learning, and optimal transport problems. Our focus includes the development and validation of learning algorithms and optimization, the establishment of new machine learning models, and practical applications. For those items, we tackle with respect to theoretic approaches and numerical evaluations. Its applications include data analysis, computer vision, video surveillance, network traffic analysis, distributed sensing, graph analysis, etc.

RESEARCH TOPICS