Large-scale optimization algorithms and its applications in machine learning. More specifically,
- Stochastic Gradient Methods (SGD, SDCA, SVRG, etc.) fors Large-scale Nonlinear Optimization
- Optimization Method in Deep Neural Network
- Parallel/Distributed Algorithms
- Large Scale Distributed Hessian-Free Optimization for Deep Neural Network, with Mudigere Dheevatsa, Martin Takáč.
- Asynchronous Distributed Stochastic dual (Block) Coordinate Ascent Method, with Martin Takáč.
- Coordinate Descent Methods for Linearly Constrained Optimization, with Martin Takáč.
- Efficient calculations of negative curvature in a Hessian Free Deep Learning framework with Ioannis Akrotirianakis, Amit Chakraborty.
- Dual Free Adaptive Mini-Batch SDCA for Empirical Risk Minimization, Phd Seminar 2016, Lehigh University.
- Dual Free SDCA for Empirical Risk Minimization with Adaptive Probabilities, NIPS 2015, Montréal, Canada.
- Estimating Portfolio Loss Probabilities with Optimal Risk Loading Coefficients and Fixed Dependency among Obligors, Siemens Corporation 2015, Corporate Technology.
- Random Coordinate Descent Method on Large-scale Optimization Problems, Coral Seminar 2015, Lehigh University.
Selected Course Projects
Explored second-order methods to training fully connected deep neural network on handwritten digits classification problem (
Designed competitive Q&A system to attain up to 39.5% accuracy by using Apache Lucene and Natural Language Toolkit, etc.. (
Used l1-regularized lasso model to recovery pictures with missing pixels. Multiple algorithms (ISTA, FISTA, GRPS) are implemented in
Matlabsoftware package to compare various of classifier technologies (SVM, Artificial Neural Network, Decision Tree, KKN) for character-image classification problem.
Pythonsoftware package to address mixed binary programming problem with branch and cut method. (Group project)
Matlabsoftware package for unconstrained nonlinear optimization using various of Nonlinear Optimization methods (GD, Newton, CG, BFGS/DFP, TR and Amijo/Wolfe).
Proposed model and developed a
Rsoftware package to estimate large-loss probability of a Portfolio with derived optimal loading coefficient.
Business Analytics and Monitoring, Siemens Corporation, Corporate Technology, Princeton, NJ.
- Portfolio credit risk, with Dr. Amit Chakraborty
- Deep learning optimization, with Dr. Ioannis Akrotirianakis
Department of Industrial and Systems Engineering, Lehigh University, Bethlehem, PA.
- Applied Engineering Statistics (Spring 2015), with Prof. Alexander (Sasha) Stolyar
- Applied Engineering Statistics (Fall 2014), with Prof. Eugene Perevalov
Department of Mathematics, Nankai University, Tianjin.
- Theory of Optimization (Spring 2014), with Prof. Qingzhi Yang
- Linear algebra (Fall 2013), with Prof. Qingzhi Yang