Hiroyuki Kasai

alt text 

Ph.D

Associate Professor
The Unviersity of Electro-Communcations, Japan

Email: kasai at is dot uec dot ac dot jp

Research interests

My research interests generally include optimization, machine learning and learning-based signal processing with those applications in communication & network systems, image & video processing, and other data analysis fields.

Biography

Hiroyuki Kasai received his B.Eng., M.Eng., and Dr.Eng. degrees in Electronics, Information, and Communication Engineering from Waseda University, Tokyo, Japan in 1996, 1998, and 2000, respectively. He was a visiting researcher at British Telecommunication BTexacT Technologies, U.K. during 2000-2001. He joined Network Laboratories, NTT DoCoMo, Japan, in 2002, and since 2007 has been an Associate Professor at The University of Electro-Communications, Tokyo. He was a senior policy researcher at Council for Science, Technology and Innovation Policy (CSTP), Cabinet Office of Japan, during 2011-2013. He was a visiting researcher at Technical University of Munich, Germany, during 2014-2015. His research interests include optimization, machine learning, and signal processing.

News (since Dec. 2017)

11-11-2018

“Fast online low-rank tensor subspace tracking by CP decomposition using recursive least squares from incomplete observations” (HK) has been accepted in Neurocomputing.

10-24-2018

“McTorch, a manifold optimization library for deep learning” (M.Meghwanshi, P.Jawanpuria, A.Kunchukuttan, HK and B.Mishra) has been accepted in NIPS workshop MLOSS2018.

10-24-2018

“Stochastic optimization library: SGDLibrary” (HK) has been accepted in NIPS workshop MLOSS2018 (splotlight).

10-08-2018

“SimpleDeepNetToolbox (Simple Deep Net Toolbox in MATLAB)” has been released.

09-22-2018

“McTorch (Manifold optimization library for deep learning)” has been released.

09-11-2018

“Fast optimization algorithm for hybrid precoding in Millimeter wave MIMO systems” (HK) has been accepted in GlobalSIP2018.

09-05-2018

“Inexact trust-region algorithm on Riemannian manifolds” (HK and B.Mishra) has been accepted in NIPS2018.

05-25-2018

“Stochastic recursive gradient on Riemannian manifolds” (HK, H.Sato and B.Mishra) has been accepted in ICML workshop GiMLi2018.

05-25-2018

“Low-rank geometric mean metric learning” (M.Bhutani, P.Jawanpuria, HK and B.Mishra) has been accepted in ICML workshop GiMLi2018.

05-18-2018

“Riemannian joint dimensionality reduction and dictionary learning on symmetric positive definite manifolds” (HK and B.Mishra) has been accepted in EUSIPCO2018.

05-18-2018

“Accelerated stochastic multiplicative update with gradient averaging for nonnegative matrix factorization” (HK) has been accepted in EUSIPCO2018.

05-12-2018

“Riemannian stochastic recursive gradient algorithm” (HK, H.Sato and B.Mishra) has been accepted in ICML2018.

04-05-2018

“SGDLibrary: A MATLAB library for stochastic optimization algorithms” (HK) has been accepted in JMLR.

01-30-2018

“Stochastic variance reduced multiplicative update for nonnegative matrix factorization” (HK) has been accepted in ICASSP2018.

12-22-2017

“Riemannian stochastic quasi-Newton algorithm with variance reduction and its convergence analysis” (HK, H.Sato and B.Mishra) has been accepted in AISTATS2018.

Contact

Please email me at kasai at is dot uec dot ac dot jp.