Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.

L1-regularized least squares with PyTorch

An Image Reconstructor that applies fast proximal gradient method (FISTA) to the wavelet transform of an image using L1 and Total Variation (TV) regularizations

Overparameterization and overfitting are common concerns when designing and training deep neural networks. Network pruning is an effective strategy used to reduce or limit the network complexity, but often suffers from time and computational intensive procedures to identify the most important connections and best performing hyperparameters. We s…

High Dimensional Portfolio Selection with Cardinality Constraints

regression algorithm implementaion from scratch with python (least-squares, regularized LS, L1-regularized LS, robust regression)

Implementation of optimization and regularization algorithms in deep neural networks from scratch

Mathematical machine learning algorithm implementations

The project encompasses the statistical analysis of a high-dimensional data using different classification, feature selection, clustering and dimension reduction techniques.

This is a mid-term project of Optimization Methods, a course of Institute of Data Science, National Cheng Kung University. This project aimed to construct the linear regression with L1 regularization and the logistic regression with L1 regularization.

This repository contains the code for the blog post on Understanding L1 and L2 regularization in machine learning. For further details, please refer to this post.