1 code implementation • 9 Sep 2023 • Feng Zhou, Antonio Cicone, Haomin Zhou
Time-frequency analysis is an important and challenging task in many applications.
1 code implementation • 4 Jul 2023 • Feng Zhou, Antonio Cicone, Haomin Zhou
Inspired by the successful applications of deep learning in fields like image processing and natural language processing, and given the lack in the literature of works in which deep learning techniques are used directly to decompose non-stationary signals into simple oscillatory components, we use the convolutional neural network, residual structure and nonlinear activation function to compute in an innovative way the local average of the signal, and study a new non-stationary signal decomposition method under the framework of deep learning.
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 • 31 Jan 2023 • Nathan Gaby, Xiaojing Ye, Haomin Zhou
Numerical experiments on different high-dimensional evolution PDEs with various initial conditions demonstrate the promising results of the proposed method.
no code implementations • 29 Jun 2022 • Haoran Sun, Hanjun Dai, Bo Dai, Haomin Zhou, Dale Schuurmans
It is known that gradient-based MCMC samplers for continuous spaces, such as Langevin Monte Carlo (LMC), can be derived as particle versions of a gradient flow that minimizes KL divergence on a Wasserstein manifold.
1 code implementation • 7 Jun 2021 • Jiaojiao Fan, Shu Liu, Shaojun Ma, Haomin Zhou, Yongxin Chen
Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another.
no code implementations • 14 Mar 2021 • Shaojun Ma, Haomin Zhou, Hongyuan Zha
We propose a novel mean field games (MFGs) based GAN(generative adversarial network) framework.
no code implementations • 5 Feb 2021 • Shu Liu, Shaojun Ma, Yongxin Chen, Hongyuan Zha, Haomin Zhou
We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions.
no code implementations • 28 Nov 2020 • Philippe Barbe, Antonio Cicone, Wing Suet Li, Haomin Zhou
Iterative filtering methods were introduced around 2010 to improve definitions and measurements of structural features in signal processing.
Numerical Analysis Numerical Analysis
no code implementations • 26 Feb 2020 • Gang Bao, Xiaojing Ye, Yaohua Zang, Haomin Zhou
We consider a weak adversarial network approach to numerically solve a class of inverse problems, including electrical impedance tomography and dynamic electrical impedance tomography problems.
no code implementations • 22 Feb 2020 • Shaojun Ma, Haodong Sun, Xiaojing Ye, Hongyuan Zha, Haomin Zhou
Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples.
no code implementations • 10 Feb 2020 • Shaojun Ma, Shu Liu, Hongyuan Zha, Haomin Zhou
Learning nonlinear dynamics from aggregate data is a challenging problem because the full trajectory of each individual is not available, namely, the individual observed at one time may not be observed at the next time point, or the identity of individual is unavailable.
1 code implementation • 18 Jul 2019 • Yaohua Zang, Gang Bao, Xiaojing Ye, Haomin Zhou
The weak solution and the test function in the weak formulation are then parameterized as the primal and adversarial networks respectively, which are alternately updated to approximate the optimal network parameter setting.
Numerical Analysis Numerical Analysis
no code implementations • 10 Feb 2018 • Ruilin Li, Xiaojing Ye, Haomin Zhou, Hongyuan Zha
We emphasize that the discrete optimal transport plays the role of a variational principle which gives rise to an optimization-based framework for modeling the observed empirical matching data.
6 code implementations • 5 Feb 2018 • Antonio Cicone, Haomin Zhou
Real life signals are in general non--stationary and non--linear.
Numerical Analysis
no code implementations • 7 Dec 2015 • Antonio Cicone, Jingfang Liu, Haomin Zhou
Hyperspectral images can be used to identify chemical plumes, however the task can be extremely challenging.
5 code implementations • 21 Nov 2014 • Antonio Cicone, Jingfang Liu, Haomin Zhou
We provide sufficient conditions on the filters that ensure the convergence of IFs applied to any $L^2$ signal.
Numerical Analysis