A reproduction of Learning Efficient Convolutional Networks through Network Slimming

Implementation of Convex Optimization algorithms

Subgradient methods for Multicommodity Network Design

Solving quadratic programming problem using subgradient optimizer

MCPy is a python library for McCormick relaxations with sub-gradients. This is quite useful for prototyping and testing new convex relaxation and global optimization algorithms.

Implementation and brief comparison of different First Order and different Proximal gradient methods, comparison of their convergence rates

R package for SGD inference

This repository contains the Python code and solutions for machine learning, including supervised and unsupervised learning, regularization, cross-validation, PCA, and support vector machines (SVM).

Convex Optimization Algorithms

Minimax NMF

Non-linear topology identification using Deep Learning. Sparsity (lasso) is enforced in the sensor connections. The non-convex and non-differentiable function is solved using sub-gradient descent algorithm.

Dual-Based Procedure and Subgradient method implementations

Optimization includes a class of methods to find global or local optima for discrete or continuous objectives; from evolutionary-based algorithms to swarm-based ones.

In this work, we consider learning sparse models in large scale setting, where the number of samples and the feature dimension can grow as large as millions or billions. Two immediate issues occur under such challenging scenarios: (i) com- putational cost; (ii) memory overhead.

Some notes on convex optimization