EDUCATION
Electrical Engineering & Computer Science, University
of Michigan, Ann Arbor
08/2023-Present(est.08/2024)
-
Ph.D. Candidate in Electrical and Computer Engineering. Advisor: Samet Oymak
Computer Science and Engineering, UCR, US
09/2018-08/2023
-
Ph.D. Candidate in Computer Science. Advisor: Samet Oymak
-
GPA: 3.93/4.0
School of Computer Science and Technology, Fudan
University, China
09/2013-06/2017
-
Degree: Bachelor of Science in Information Security. Advisor: Yanqiu Chen
RESEARCH INTERESTS
My research interests are statistical machine learning and optimization, including
robust neural network training, network pruning, semi-supervised learning, and
bilevel optimization. I am highly interested in learning on noisy datasets or
datasets that are rarely labeled or even unlabeled. My current research project is
exploring LLM-based multiagent system in competing environment.
SELECTED RESEARCH EXPERIENCE
Gradient descent with early stopping is probably robust
to label noise for overparameterized neural networks.
Published
on AISTATS 2020, 305 citations
- 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.
FEDNEST: Federated Bilevel, Minimax, and Compositional
optimization
Published
on ICML 2022, oral, 2% acceptance
- Proposed FEDNEST: A federated gradient-based method to address nested
optimization problems.
- Provided provable convergence rate for FEDNEST in the presence of heterogeneous
and introduced variations for bilevel, minimax and compositional optimization.
Experiments on hyperparameter and hyper-representation learning demonstrate the
benefit of FEDNEST in practice.
AutoBalance: Optimized Loss Functions for Imbalanced
Data
Published
on NeurIPS 2021
- Established a bi-level optimization framework that automatically designs a
training loss function to optimize a blend of accuracy and fairness-seeking
objectives, such as long-tailed data and group imbalanced data.
- Demonstrated that the designed personalized treatment for class/group imbalanced
dataset overperforms state-of-the-art approaches by extensive evaluations.
Generalization Guarantees for Neural Architecture
Search with Train-Validation Split.
Published
on ICML 2021
- Demonstrated that validation loss of a near-minimal validation set can be
indicative of the true test loss. The theory is established for continuous
search spaces which relevant to popular differentiable NAS methods.
- Established generalization bounds for NAS problems with an emphasis on an
activation search problem. Proved that train-validation procedure can produce
best architecture even the model overfits to training data.
Generalization, Adaptation and Low-Rank Representation
in Neural Networks.
Published
on Asilomar Conference, 61 citations
- 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.
WORK & PROJECTS EXPERIENCE
Student Researcher at Google LLC., RankLab team
2022 Sep-Nov
Software Engineer Intern at Google LLC., RankLab team
2022 Jun-Nov
- Focused on noisy detection on imbalanced dataset.
Software Engineer Intern at Google LLC., YouTube Shorts
team
2021 Jun-Nov
- Improved user profiling model to enhance recommendation system in YouTube Shorts
ranking team.
GPU-Accelerated Deep Learning Framework: Mini-Caffe
2019
- 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:
2019
- 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.
2017
- 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.
PUBLICATIONS
- Xuechen Z., Mingchen L., Vakilian V., et al. "Class-attribute
Priors: Adapting Optimization to Heterogeneity and Fairness Objective." AutoML
Conference 2023.
- Xuechen Z., Mingchen L., Xiangyu C. et al. "FedYolo: Augmenting
Federated Learning with Pretrained Transformers." arXiv preprint
arXiv:2307.04905 (2023).
- Tarzanagh D A, Mingchen L., Sharma P, et al. "Federated
Multi-Sequence Stochastic Approximation with Local Hypergradient Estimation."
arXiv preprint arXiv:2306.01648 (2023).
- Tarzanagh D A, Mingchen L., Thrampoulidis C, et al. "FEDNEST:
Federated Bilevel, Minimax, and Compositional Optimization." International
Conference on Machine Learning (ICML 2022, oral, 2% acceptance, 35 citations)
- Mingchen L., Mahdi Soltanolkotabi, and Samet Oymak. "Gradient descent with early
stopping is provably robust to label noise for overparameterized neural
networks." International Conference on Artificial Intelligence and
Statistics. 2020. (AISTATS 2020, 305 Citations)
- Mingchen L., Xuechen Z., Thrampoulidis, C., Jiasi C. & Oymak,
S. "Autobalance: Optimized loss functions for imbalanced data." NeurIPS 2021, 28
citations.
- Oymak, S., Mingchen L., and Soltanolkotabi, M. "Generalization
Guarantees for Neural Architecture Search with Train-Validation Split."
International Conference on Machine Learning (ICML 2021, 10 citations).
- Mingchen L., Sattar, Y., Thrampoulidis, C., & Oymak, S. (2020).
Exploring Weight Importance and
Hessian Bias in Model Pruning. arXiv preprint arXiv:2006.10903. (4
citations)
- Chan, Y., Mingchen L., and Oymak, S. "On the Marginal Benefit
of Active Learning: Does Self-Supervision Eat Its Cake?" ICASSP 2021-2021 IEEE
International Conference on Acoustics, Speech and Signal Processing (ICASSP).
IEEE, 2021. (21 citations)
- Oymak, S., Fabian, Z., Mingchen L., & Soltanolkotabi, M.
(2019). Generalization guarantees
for neural networks via harnessing the low-rank structure of the
Jacobian. arXiv preprint arXiv:1906.05392. (61 citations)
- Luchao T.; Mingchen L.; Hao Y.; et al. “Robust 3D Human
Detection in Complex Environments with Depth Camera”, 2018 IEEE
Transactions on Multimedia (TMM) (41 citations)
- Luchao T.; Mingchen L.; Guyue Z.; et al. "Human Detection with
Super-pixel Segmentation and Random Ferns Classification Using RGB-D
Camera", 2017 IEEE International Conference on Multimedia and Expo
(ICME), Hong Kong, China, July 10-14, 2017
- Luchao T.; Guyue Z.; Mingchen L.; et al., "Reliably Detecting
Humans in Crowded and Dynamic Environments Using RGB-D Camera", 2016
IEEE International Conference on Multimedia and Expo (ICME), Seattle, United
States, July 11-15, 2016
SKILLS & ACADEMIC SERVICES
Technologies
- Machine Learning programming using PyTorch, TensorFlow and JAX, GPU programming.
Reviewer Experience
- Reviewer of NeurIPS, ICML, AISTATS, ICLR, CVPR and KDD.
Teaching Experience
- Teach assistant of Deep Learning, Artificial Intelligence, Data Science courses
in UCR.
AWARD
Dissertation Year Program (DYP) fellowship, UCR, CS Department
2022
Second class scholarship of Fudan University, twice, 4/32
2015 & 2017
Third class scholarship of Fudan University
2016