1 code implementation • 12 Dec 2023 • Yun Liao, Junfan Li, Shizhong Liao, QinGhua Hu, Jianwu Dang
In this paper, we study the mistake bound of online kernel learning on a budget.
no code implementations • 29 Aug 2023 • Yun Liao, Yide Di, Hao Zhou, Kaijun Zhu, Mingyu Lu, Yijia Zhang, Qing Duan, Junhui Liu
Local feature matching remains a challenging task, primarily due to difficulties in matching sparse keypoints and low-texture regions.
no code implementations • 18 May 2023 • Yun Liao, Ruihui Xu
This study employs the annual unbalanced panel data of 42 listed banks in China from 2006 to 2021, adopts the non-radial and non-oriented super-efficiency Data envelopment analysis (Super-SBM-UND-VRS based DEA) model considering NPL as undesired output.
no code implementations • 26 Feb 2023 • Lingjie Kong, Yun Liao
In the initial PAN paper, it uses a path integral based graph neural networks for graph prediction.
no code implementations • 3 Jul 2022 • Yun Liao, Seyyed Ali Hashemi, Hengjie Yang, John M. Cioffi
In addition, when an IMP model trained on a length-128 polar code directly applies to the construction of polar codes with different code rates and blocklengths, simulations show that these polar code constructions deliver comparable performance to the 5G polar codes.
no code implementations • 19 Sep 2020 • Yun Liao, Seyyed Ali Hashemi, John Cioffi, Andrea Goldsmith
This paper formulates the polar-code construction problem for the successive-cancellation list (SCL) decoder as a maze-traversing game, which can be solved by reinforcement learning techniques.
no code implementations • 25 Jul 2019 • Yun Liao, Nariman Farsad, Nir Shlezinger, Yonina C. Eldar, Andrea J. Goldsmith
This paper proposes to use a deep neural network (DNN)-based symbol detector for mmWave systems such that CSI acquisition can be bypassed.