Renkun Ni

倪仁坤


Ph.D. student
Department of Computer Science
University of Maryland, College Park

Bio

I am a third year PhD student in Computer Science at University of Maryland, under the supervision of Prof. Tom Goldstein. Before that, I received my M.S. degree in Statistics from University of Virginia in 2018 and B.S. degree in Applied Mathmetics from Tongji University in 2014, during which I was fortunate to be advised by Prof. Quanquan Gu at University of Virginia and Dr. Jianguo Li at Intel Labs China. My research interests mainly focus on the intersection of machine learning and optimization, and target applications in computer vision and signal processing.

News

  • [July 2021] One paper is accepted by the International Conference on Machine Learning (ICML) 2021.
  • [Jan 2021] One paper is accepted by the International Conference on Learning Representations (ICLR) 2021.
  • [Dec 2020] One patent is issued for automatic muscle segmentation.
  • [Dec 2020] Renkun will host a virtual poster session in the NeurIPS Workshop on Meta-Learning.
  • [Nov 2020] One paper is accepted by the NeurIPS Workshop on Meta-Learning.

    • Publications

  • Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, Tom Goldstein, "Data Augmentation for Meta-Learning", in the proceeding of the International Conference on Machine Learning (ICML), 2021.[arxiv][code]
  • Renkun Ni, Hong-min Chu, Oscar Castaneda, Ping-yeh Chiang, Christoph Studor, Tom Goldstein, "WrapNet: Neural Net Inference with Ultra-Low-Precision Arithmetic", in the proceeding of the International Conference on Learning Representations (ICLR), 2021.[arxiv]
  • Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong, Tom Goldstein, "Data Augmentation for Meta-Learning", accepted by NeurIPS Workshop on Meta-Learning (MetaLearn), 2020.[arxiv][code]
  • Micah Goldblum, Steven Reich*, Liam Fowl*, Renkun Ni*, Valeriia Cherepanova*, Tom Goldstein, "Unraveling Meta-Learning: Understanding Feature Representations for Few-Shot Tasks", in the proceeding of the International Conference on Machine Learning (ICML), 2020.[arxiv][code]
  • Ping-Yeh Chiang, Jonas Geiping, Micah Goldblum, Tom Goldstein, Renkun Ni, Steven Reich, Ali Shafahi, "WITCHcraft: Efficient PGD attacks with random step size", in the proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020.[arxiv]
  • Ping-Yeh Chiang*, Renkun Ni*, Ahmed Abdelkader, Chen Zhu, Christoph Studor, Tom Goldstein, "Certified Defenses for Adversarial Patches", in the proceeding of the International Conference on Learning Representations (ICLR), 2020.[arxiv][code]
  • Tianyuan Xie, Katherine B Crump, Renkun Ni, Craig H Meyer, Joseph M Hart, Silvia S Blemker, Xue Feng, "Quantitative relationships between individual lower-limb muscle volumes and jump and sprint performances of basketball players", aceepted by Journal of Strength & Conditioning Research, 2020.
  • Renkun Ni, Craig H Meyer, Silvia S Blemker, Joseph M Hart, Xue Feng, "Automatic segmentation of all lower limb muscles from high-resolution magnetic resonance imaging using a cascaded three-dimensional deep convolutional neural network", accepted by Journal of Medical Imaging, 2019.
  • Yinpeng Dong, Renkun Ni, Jianguo Li, Yurong Chen, Jun Zhu, Hang Su, "Learning Accurate Low-Bit Deep Neural Networks with Stochastic Quantization", in the proceedings of the British Machine Vision Conference (BMVC), 2017.[arxiv][code]
  • Renkun Ni, Quanquan Gu, "Optimal Statistical and Computational Rates for One Bit Matrix Completion", in the proceedings of the International Conference on Artificial Intelligence and Statistics (AISTATS), 2016.[arxiv]

    • Patents

  • Xue Feng, Renkun Ni, Anudeep Konda, Silvia S Blemker, Joseph M Hart, Craig H Meyer, "System and method for automatic segmentation of muscles from high-resolution mri using 3d deep convolutional neural network", U.S. Patent Application No. 16/724,192.
  • Yurong Chen, Jianguo Li, Renkun Ni, "Efficient neural networks with elaborate matrix structures in machine learning environments", U.S. Patent Application No. 16/632,145.

    • Contacts

    Iribe Center, Office 5120
    College Park, MD 20740
    rn9zm-{AT}-cs-DOT-umd-DOT-edu

    You'll Never Walk Alone


    Renkun © last update Aug 2021