Ph.D. student in Computer Science
University of Southern California
Foundation of Deep Learning
Machine Learning for Physics Simulation
and Masaaki Imaizumi.
Quasi-potential theory for escape problem: Quantitative sharpness effect on SGD's escape from local minima.
, Ken-ichi Nomura, Pankaj Rajak, Taufeq Mohammed, Ankit Mishra, Aravind Krishnamoorthy and Aiichiro Nakano.
Sharpness-Aware Minimization for Robust Molecular Dynamics Simulations.
NeurIPS 2021 workshop on Machine Learning and the Physical Sciences.
, Takuo Hamaguchi, Masaaki Imaizumi.
Minimum sharpness: Scale-invariant parameter-robustness of neural networks.
International Conference on Machine Learning Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI (ICML 2021 Workshop paper).
, Chris Wojtan, Nils Thuerey, Takeo Igarashi, and Ryoichi Ando.
Simulating Liquids on Dynamically Warping Grids.
IEEE Transactions on Visualization and Computer Graphics (TVCG 2018)
, Toby Chong, Daisuke Sakamoto, Natsuki Miyata, Mitsunori Tada, Takashi Okuma, Takeshi Kurata, Masaaki Mochimaru and Takeo Igarashi.
An Asymmetric Collaborative System for Architectural-scale Space Design.
The 16th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and its Applications in Industry (VRCAI 2018)
Shunsuke Saito, Liwen Hu, Chongyang Ma,
, Linjie Luo, Hao Li.
3D Hair Synthesis Using Volumetric Variational Autoencoders.
ACM Transactions on Graphics, Proceedings of the 11th ACM SIGGRAPH Conference and Exhibition in Asia (SIGGRAPH Asia 2018)
, Yuta Sugiura, Daisuke Sakamoto, Natsuki Miyata, Mitsunori Tada, Takashi Okuma, Takeshi Kurata, Masaaki Mochimaru and Takeo Igarashi.
Dollhouse VR: A Multi-view, Multi-user Collaborative Design Workspace with VR Technology.
In ACM SIGGRAPH Asia 2015 Emerging Technologies (SA '15). ACM, New York, NY, USA.
Lecturing as a TA
Software Contribution to
Note: Kramer's escape problem with SGLD and SGD
Approximate Residual Balancing
I'm a Magician
Simple 2D Fluid Simulation