I moved to Texas A&M University. Please check my new webpage.
- Yongjian Zhong (Phd student, will join the group in Fall 2021)
- Bokun Wang (Phd student, will join the group in Fall 2021)
- Yao Yao (Phd student at AMCS, joined the group in Fall 2020)
- Quanqi Hu (Phd student at AMCS, joined the group in Fall 2020)
- Dixian Zhu (PhD student, joined the group in 2018)
- Zhuoning Yuan (PhD student, joined the group 2018)
- Qi Qi (PhD student, joined the group 2018)
- Zhishuai Guo (PhD student, joined the group 2018)
- Xin Man (Phd student, joined the group in Fall 2016)
- Mingrui Liu (Phd 2020), Nonconvex Min-Max Optimization in Deep Learning: Algorithms and Applications. First Appointment: tenure-track Assistant Professor at George Mason University (fall 2021)
- Yan Yan (Visiting student: 02/2016 - 07/2016, Postdoc Research Associate: 09/2018 - 09/2020) First Appointment: Assistant Professor at WSU
- Zaiyi Chen (Visiting student, 09/2016 - 09/2017). First Appointment: Cainiao
- Yi Xu (PhD 2019), Accelerate Convex Optimization in Machine Learning by Leveraging Structural Conditions. Associate Professor at Dalian University of Technology, China
- Zhe Li (PhD 2018), Optimizing Neural Network Structures: Faster Speed, Smaller Size, Less Tuning. First Appointment: Apple Inc.
- Xiaoxuan Zhang (PhD 2018), Online Learning for Imbalanced Data: Optimizing Asymmetric Measures. First Appointment: Ancestry Inc.
FAI: Advancing Optimization for Threshold-Agnostic Fair AI Systems,
NSF-Amazon Joint Fair AI Program (2022-2025). Lead PI
Collaborative Research: RI: Small: Robust Deep Learning with Big Imbalanced Data,
NSF RI Core Program (2021-2024). Lead PI
Collaborative Research: Online Data Stream Fusion and Deep Learning for Virtual Meter in Smart Power Distribution Systems,
NSF EPCN-Energy-Power-Control-Networks Program (2019-2022). PI (Collaborative Proposal with PIs from WSU)
- CAREER: Advancing Constrained and Non-Convex Learning,
NSF Early Career Development Program (2019-2024). Details
- SCH: INT: Collaborative Research: A Framework for Optimizing Hearing Aids In Situ Based on Patient Feedback, Auditory Context, and Audiologist Input,
NSF Smart and Connected Health Program (2019-2022). Co-PI (with PI Octav Chipara).
- New Algorithms of Online Machine Learning for Big Data,
NSF BIGDATA Program (2015-2018). PI (with Co-PI Padmini Srinivasa). Details
- Scaling up Distance Metric Learning for Large-scale Ultrahigh-dimensional Data,
NSF CRII Program (2015-2017). PI. Details
- Deep Learning for Fine-grained Image Classification,
NEC Labs America (2014-2015)
I am interested in machine learning and optimization and its applications to big data analytics.
My current research topics include:
Some old research topics during PhD studies include:
- Deep AUC Maximization
To develope effective and efficient algorithms for deep learning with AUC objectives.
- Non-Convex Optimization Algorithms
To develope provable and practical optimization algorithms for solving non-convex problems in machine learning
[Unified Momentum] , [NEON] , [Adaptive NCD], [Stagewise Optimization for DL] , [Stagewise Katyusha] , [Non-Convex Concave Min-Max] , [Non-Convex Non-Concave Min-Max]
- Faster Convergent Algorithms by Leveraging Error Bound Condition
To develope faster convergent optimization algorithms by leveraging local and global error bound conditions
[RSG] , [HOPS] , [ASSG], [Adaptive Admm] , [adaSVRG] , [adaAGC] , [SadaGrad] , [LogProj] , [ada-Frank-Wolfe]
- Large-scale Stochastic Optimization
To develope efficient algorithms for stochastic optimization for learning from large-scale high-dimensional data.
- Online Optimization
To develope new online convex optimization algorithms.
To understand, design and optimize deep neural networks for large-scale image classification.
See demo on flower, food and vehicle recognition, collaborating with NEC Labs America.
Randomized Algorithms for Big Data Analytics
Developing randomized algorithms for solving big data machine learning problems. See here.
Distributed Optimization for Big Data
Developed a practical distributed optimization for solving big data classification and regression problems. See Software.
Social Network Analysis
Developed algorithms for detecting communities and their dynamic evolutions in Social Networks.
Learning from Noisy Labels
Developed algorithms and theories for learning from Noisy labels.
Multiple Kernel Learning
Developed efficient and robust algorithms for multiple kernel learning.
- Improved Bounds for the Nystrom method
Developed several improved bounds for the Nystrom method under larger eigengap condition and power law eigenvalue distribution; and the theory of their
applications to large-scale kernel learning.