447 citations · 733 across the 44 of their papers we have counts for
8 papers · 1 filter
RRCNN: A novel signal decomposition approach based on recurrent residue convolutional neural network
Feng Zhou, Antonio Cicone, Haomin Zhou
The decomposition of non-stationary signals is an important and challenging task in the field of signal time-frequency analysis. In the recent two decades, many signal decompositio…
Why Shallow Networks Struggle to Approximate and Learn High Frequencies
Shijun Zhang, Hongkai Zhao, Yimin Zhong +1
In this work, we present a comprehensive study combining mathematical and computational analysis to explain why a two-layer neural network struggles to handle high frequencies in b…
Discrete Langevin Sampler via Wasserstein Gradient Flow
Haoran Sun, Hanjun Dai, Bo Dai +2
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 di…
Neural Monge Map estimation and its applications
Jiaojiao Fan, Shu Liu, Shaojun Ma +2
Monge map refers to the optimal transport map between two probability distributions and provides a principled approach to transform one distribution to another. Neural network base…
Mean Field Game GAN
Shaojun Ma, Haomin Zhou, Hongyuan Zha
We propose a novel mean field games (MFGs) based GAN(generative adversarial network) framework. To be specific, we utilize the Hopf formula in density space to rewrite MFGs as a pr…
Learning High Dimensional Wasserstein Geodesics
Shu Liu, Shaojun Ma, Yongxin Chen +2
We propose a new formulation and learning strategy for computing the Wasserstein geodesic between two probability distributions in high dimensions. By applying the method of Lagran…
Learning Cost Functions for Optimal Transport
Shaojun Ma, Haodong Sun, Xiaojing Ye +2
Inverse optimal transport (OT) refers to the problem of learning the cost function for OT from observed transport plan or its samples. In this paper, we derive an unconstrained con…
Learning Stochastic Behaviour from Aggregate Data
Shaojun Ma, Shu Liu, Hongyuan Zha +1
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 tim…