òòò½Íø

Atsushi Nitanda is a Principal Scientist at A*STAR Centre for Frontier AI Research (A*STAR CFAR). He also holds a joint appointment as an Associate Professor in the College of Computing and Data Science (CCDS) at Nanyang Technological University, òòò½Íø(NTU Singapore).

Prior to his current position, he was an Associate Professor at the Kyushu Institute of Technology and an Assistant Professor at the University of Tokyo. Previously, he worked at NTTDATA-MSI in Japan as a researcher. He obtained his Ph.D. in Information Science and Technology from the University of Tokyo in 2018.

His research primarily focuses on the mathematical foundations of machine learning, stochastic optimisation, and sampling methods, with the goal of understanding the capabilities of machine and deep learning models through the lens of optimisation dynamics and sampling-based approaches.

For example, he has worked on stochastic gradient descent, acceleration methods, and the learning theory of neural networks. In particular, he has made significant contributions to the theoretical foundations of mean-field Langevin dynamics, including convergence analysis and the propagation of chaos.

In 2021, he received the Outstanding Paper Award at ICLR and the Dean’s Awards from the University of Tokyo for academic achievement in doctoral and master’s research in 2019 and 2009 respectively. Following his selection as a TMLR expert reviewer, he has served as an action editor for TMLR, editorial board reviewer for JMLR, editorial board member for IEICE Transactions, and IBISML committee member.

Contact: atsushi_nitanda@a-star.edu.sg