Current Research

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

Working Papers

  • 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

  • Optimization Method in Machine Learning

    Explored second-order methods to training fully connected deep neural network on handwritten digits classification problem (Matlab).

  • Massive Data Mining

    Designed competitive Q&A system to attain up to 39.5% accuracy by using Apache Lucene and Natural Language Toolkit, etc.. (Python)

  • Computation Methods

    Used l1-regularized lasso model to recovery pictures with missing pixels. Multiple algorithms (ISTA, FISTA, GRPS) are implemented in C++ and compared.

  • Pattern Recognition

    Implemented a Matlab software package to compare various of classifier technologies (SVM, Artificial Neural Network, Decision Tree, KKN) for character-image classification problem.

  • Integer Programming

    Implemented a Python software package to address mixed binary programming problem with branch and cut method. (Group project)

  • Nonlinear Programming

    Developed a Matlab software package for unconstrained nonlinear optimization using various of Nonlinear Optimization methods (GD, Newton, CG, BFGS/DFP, TR and Amijo/Wolfe).

  • Credit Portfolio Risk

    Proposed model and developed a R software package to estimate large-loss probability of a Portfolio with derived optimal loading coefficient.


Research Assistant

Business Analytics and Monitoring, Siemens Corporation, Corporate Technology, Princeton, NJ.

  • Portfolio credit risk, with Dr. Amit Chakraborty
  • Deep learning optimization, with Dr. Ioannis Akrotirianakis

Teaching Assistant

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

Teaching Assistant

Department of Mathematics, Nankai University, Tianjin.

  • Theory of Optimization (Spring 2014), with Prof. Qingzhi Yang
  • Linear algebra (Fall 2013), with Prof. Qingzhi Yang