Minghan Yang

About Minghan Yang

Minghan Yang, With an exceptional h-index of 4 and a recent h-index of 4 (since 2020), a distinguished researcher at Peking University, specializes in the field of optimization, machine learning.

His recent articles reflect a diverse array of research interests and contributions to the field:

Riemannian natural gradient methods

An efficient Fisher matrix approximation method for large-scale neural network optimization

Sketch-based empirical natural gradient methods for deep learning

A stochastic extra-step quasi-Newton method for nonsmooth nonconvex optimization

Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods

Minghan Yang Information

University

Position

___

Citations(all)

53

Citations(since 2020)

53

Cited By

5

hIndex(all)

4

hIndex(since 2020)

4

i10Index(all)

2

i10Index(since 2020)

2

Email

University Profile Page

Google Scholar

Minghan Yang Skills & Research Interests

optimization

machine learning

Top articles of Minghan Yang

Riemannian natural gradient methods

SIAM Journal on Scientific Computing

2024/2/29

An efficient Fisher matrix approximation method for large-scale neural network optimization

IEEE Transactions on Pattern Analysis and Machine Intelligence

2022/10/11

Sketch-based empirical natural gradient methods for deep learning

Journal of Scientific Computing

2022/9

A stochastic extra-step quasi-Newton method for nonsmooth nonconvex optimization

Mathematical Programming

2022/7/1

Enhance Curvature Information by Structured Stochastic Quasi-Newton Methods

2021

See List of Professors in Minghan Yang University(Peking University)