Mingchen Li


Department of Computer Science and Engineering, UCR, US


  • Ph.D. Candidate in Computer Science.
  • Advisor: Samet Oymak
  • GPA: 3.93/4.0

School of Computer Science and Technology, Fudan University, China


  • Degree: Bachelor of Science in Information Security


Gradient descent with early stopping is probably robust to label noise for overparameterized neural networks.

Published on AISTATS 2020

  • Demonstrated that large neural networks can overfit to noise, which hurt the accuracy.
  • Proved that a large neural network becomes provably robust to label noise when trained with early stopping.

Generalization, Adaptation and Low-Rank Representation in Neural Networks.

Published on Asilomar Conference

  • Demonstrated that Jacobian of a neural network exhibit low-rank structure with a few large singular values and many small ones leading to low-dimensional information space.
  • Proved that learning on the information space with large singular values is fast and can generalize well but learning on the nuisance space with smaller singular values can impede optimization and generalization.

Exploring Weight Importance and Hessian Bias in Model Pruning

arXiv preprint, in submission

  • Counterintuitively, proved that pruning small network weights can provably hurt more than pruning large network weights.
  • Established high-dimensional asymptotic bounds in neural networks pruning.


GPU-Accelerated Deep Learning Framework: Mini-Caffe


  • Designed and implemented a user-friendly GPU accelerated Caffe-like deep learning framework using C++ and CUDA for Convolution, Fully Connected, ReLU, Local Response Normalization, and Batch Normalization layers. Source code available at https://github.com/DavyVan/MiniCaffe

Data Mining: Behavior-Based Software Malware Detection:


  • Designed and implemented a novel feature extraction scheme consisting of behavior counting and PCA-based features for the dataset provided by Qihoo360 DataCon. Trained a Neural Network to identify malware software.

Software Engineering Intern at Shanghai ShanCe Technologies Company Ltd.


  • Develop a visual trading system consisting of a backend server and web interface using C++, HTML, SQL, JavaScript, and Flask framework to deploy strategies, view stocks and futures information on the website.



Reviewer of ICLR 2021 and AISTATS 2021

Member of Technology Department, Fudan University Students Web Platform


Position: Software Engineering Intern

Description: Develop the server of a graphics trading system consisting of the executor and the http server, so that users can realize bulk order, conditional order, position and market information check

  • Took charge of the routine maintenance and information distribution
  • Acquired the development skills of ASP website

Volunteer to teach local middle school students math



Second class scholarship of Fudan University, twice, 4/32


Third class scholarship of Fudan University


First class prize in National Olympiad in Informatics, Henan Province