2 citations · 5 across the 6 of their papers we have counts for
6 papers
Reverse Diffusion Monte Carlo
Xunpeng Huang, Hanze Dong, Yifan Hao +2
We propose a Monte Carlo sampler from the reverse diffusion process. Unlike the practice of diffusion models, where the intermediary updates -- the score functions -- are learned w…
Mean-Field Analysis of Two-Layer Neural Networks: Global Optimality with Linear Convergence Rates
Jingwei Zhang, Xunpeng Huang, Jincheng Yu
We consider optimizing two-layer neural networks in the mean-field regime where the learning dynamics of network weights can be approximated by the evolution in the space of probab…
ACMo: Angle-Calibrated Moment Methods for Stochastic Optimization
Xunpeng Huang, Runxin Xu, Hao Zhou +3
Due to its simplicity and outstanding ability to generalize, stochastic gradient descent (SGD) is still the most widely used optimization method despite its slow convergence. Meanw…
Adaptive Gradient Methods Can Be Provably Faster than SGD after Finite Epochs
Xunpeng Huang, Hao Zhou, Runxin Xu +2
Adaptive gradient methods have attracted much attention of machine learning communities due to the high efficiency. However their acceleration effect in practice, especially in neu…
SPAN: A Stochastic Projected Approximate Newton Method
Xunpeng Huang, Xianfeng Liang, Zhengyang Liu +4
Second-order optimization methods have desirable convergence properties. However, the exact Newton method requires expensive computation for the Hessian and its inverse. In this pa…
Enhancing Network Embedding with Auxiliary Information: An Explicit Matrix Factorization Perspective
Junliang Guo, Linli Xu, Xunpeng Huang +1
Recent advances in the field of network embedding have shown the low-dimensional network representation is playing a critical role in network analysis. However, most of the existin…