||Stochastic (block) BFGS method for
empirical risk minimization problem with
logistic loss and L2
||A suite of randomized methods for
positive definite matrices implemented in MATLAB. Related
||A lab for testing and comparing
methods for solving linear systems. Implemented in
||A framework for communication-efficient
distributed optimization for machine learning.
Accelerated, Parallel and PROXimal coordinate
is an efficient C++ code based on this paper.
implement PCDM (parallel coordinate descent), SDCA
coordinate ascent) and AGD (Accelerated Gradient
Semi-stochastic gradient descent method for fast training of L2 regularized logistic regression. This is an efficient C++ code (can be called from MATLAB), based on this paper.
|Serial [1 5], parallel [2 3 4] and distributed [6 7] coordinate descent code for big data optimization. The parallel and distributed codes can solve LASSO instances with terabyte matrices and billions of features, and are scalable.|
Associate Professor (Reader)
in Mathematical Sciences