no code implementations • 13 Jul 2023 • Shijun Zhang, Jianfeng Lu, Hongkai Zhao
This paper explores the expressive power of deep neural networks for a diverse range of activation functions.
no code implementations • 29 Jun 2023 • Shijun Zhang, Hongkai Zhao, Yimin Zhong, Haomin Zhou
In this work, a comprehensive numerical study involving analysis and experiments shows why a two-layer neural network has difficulties handling high frequencies in approximation and learning when machine precision and computation cost are important factors in real practice.
no code implementations • 29 Jan 2023 • Shijun Zhang, Jianfeng Lu, Hongkai Zhao
This paper explores the expressive power of deep neural networks through the framework of function compositions.
1 code implementation • CVPR 2021 • Rui Xiang, Rongjie Lai, Hongkai Zhao
The key idea is to use dual information, such as spatial and spectral, or local and global features, in a complementary and effective way, and extract more accurate information from current iteration to use for the next iteration.
no code implementations • CVPR 2020 • Rui Xiang, Rongjie Lai, Hongkai Zhao
To solve the resulting quadratic assignment problem efficiently, the two key ideas of our iterative algorithm are: 1) select pairs with good (approximate) correspondence as anchor points, 2) solve a regularized quadratic assignment problem only in the neighborhood of selected anchor points through sparsity control.
no code implementations • 1 Jul 2019 • Sijing Li, Zhiwen Zhang, Hongkai Zhao
We propose a data-driven approach to solve multiscale elliptic PDEs with random coefficients based on the intrinsic low dimension structure of the underlying elliptic differential operators.
no code implementations • 6 Feb 2016 • Cheng Zhang, Babak Shahbaba, Hongkai Zhao
Traditionally, the field of computational Bayesian statistics has been divided into two main subfields: variational methods and Markov chain Monte Carlo (MCMC).
1 code implementation • 18 Jun 2015 • Cheng Zhang, Babak Shahbaba, Hongkai Zhao
To this end, we build a surrogate function to approximate the target distribution using properly chosen random bases and an efficient optimization process.