Yiping Lu

Undergraduate

Department of Scientific & Engineering Computing
School of mathematical sciences
Peking University
The elite undergraduate training program of School of Mathematical Sciences in Peking University.(Both applied math and pure math track)

Email: luyiping9712 at pku dot edu dot cn
Contact: No. 5 Yiheyuan Road Beijing, 100871 People's Republic of China


Produced by l0 image smoothing and Canny edge detector.

Original image see here.

Biography [CV]

I am a last year undergraduate student in School Of Mathimatical Science at Peking University, majoring Information and Computing Science advised by Prof.Bin Dong. I'm also enjoy working with prof. Liwei Wang on thoerical machine learning. I'm a visiting student at MIT CSAIL under the supervision of Prof. Justin Solomon during summer 2018. I'm now a research intern at MSRA(Microsoft Research Asia) working on Bayesian Deep Learning. (Mentor: Visual Computing Group David Wipf)

I will apply for Ph.D this year and I am interested in both cs/ml and math programs. Also open to one/half-year visiting research position currently. If you're interested, don’t hesitate to contact me. My information is attached below and more information is demonstrate at introduction on my projects.

Research Statment(2018/11): [pdf link]

Schedule meeting? see here.

If you are interested in what I'm working on please see the project page:[link]

Key Word: Numerical Differential Equations, Image Processing, Deep Learning, Wavelet Analysis, Inverse Problem.

Research Highlight

Reviews:

1.Dynamic System and Optimal Control Perspective of Deep Learning: [pdf] (ACML2018,Tutorial Track [link])

Research Papers:

      
Bin Dong, Haochen Ju, Yiping Lu, Zuoqiang Shi. " CURE: Curvature Regularization For Missing Data Recovery ." Submitted. (Alphabetical Order.)

[ paper] [ arXiv] [code] [ slide] [Code] [Project Page]

Highlight! We design a new curvature based regularizer to enforce the patch manifold to be a low dimension smooth manifold. You can use CURE to cure your missing data!

Zichao Long, Yiping Lu, Bin Dong. " PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network" Submitted.

[ paper] [ arXiv] [code] [ slide] [ project page]

A new version PDE-NET focusing more on model recovery.

Bin Dong,Ting Lin, Yiping Lu, Zuowei Shen. " A New Edge Driven Wavelet Frame Image Restoration Model: The Mumford--Shah functional, Unnatural Zero Norm Minimization And Beyond" In Preparation(Alphabetical Order.)

[ paper] [ arXiv] [code] [ slide] [ project page]

Highlight! We give a geometry explanation of wavelet l0 spasity.

Xiaoshuai Zhang*, Yiping Lu*, Jiaying Liu, Bin Dong. "Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration" Seventh International Conference on Learning Representations(ICLR) 2019(*equal contribution)

[ paper] [ arXiv] [code] [ slide] [ project page] [Open Review]

Highlight! An RNN with dynamic unfolding times for blind image denoising/restoration.

Yiping Lu, Aoxiao Zhong, Quanzheng Li, Bin Dong. "Beyond Finite Layer Neural Network:Bridging Deep Architects and Numerical Differential Equations" Thirty-fifth International Conference on Machine Learning (ICML), 2018

[paper] [arXiv] [project page] [slide][ bibtex][Poster]

Highlight! We build a connection between numerical differential equation and network designing.

Zichao long*, Yiping Lu*, Xianzhong Ma*, Bin Dong. "PDE-Net:Learning PDEs From Data",Thirty-fifth International Conference on Machine Learning (ICML), 2018(*equal contribution)

[paper] [arXiv] [code] [Supplementary Materials][ bibtex]

Highlight! We want to discover physic law from observed data by deep learning!

My Calender

Please schedule meeting with my Google Calendar account: 2prime97@gmail.com.


© Yiping Lu | Last updated: 04/01/2019

Powered By Bootstrap & Jemdoc

Visitors(From:23/10/2017):

url and counting visits
Accurate Visits

Theory without practice is empty, but equally, practice without theory is blind. ---- I. Kant

People who wish to analyze nature without using mathematics must settle for a reduced understanding. ---- Richard Feynman