mloss | Projects submitted by ryota.

DAL 1.05

by ryota - May 3, 2011, 07:00:43 CET [ ] 9262 views, 1551 downloads, 1 subscription

About: DAL is an efficient and flexibible MATLAB toolbox for sparse learning/reconstruction based on the augmented Lagrangian method.

Changes:

35% faster group lasso.
Sparse connectivity inference example added (s_test_hsgl.m).
Non-negative lasso (thanks to Shigeyuki Oba).
Uses Mark Tygert's pca.m for SVD (PROPACK is not required anymore).

Authors: Ryota Tomioka
License: Mit
Programming Language: Matlab

Operating System: Agnostic
Data Formats: Agnostic
Tags: Optimization, Trace Norm, Group Lasso, Lasso, Sparse Learning, L1 Regularization, Logistic Regression

Logistic regression with dual spectral regularization 1.0

by ryota - April 27, 2008, 08:44:51 CET [ ] 4271 views, 1030 downloads, 1 subscription

About: It solves a classification problem over symmetric matrices with dual spectral norm (trace norm) regularization using a simple interior point method. It was successfully applied to single trial EEG [...]

Changes:

Initial Announcement on mloss.org.

Authors: Ryota Tomioka
License: Gpl
Programming Language: Matlab, Cvx

Operating System: Linux, Macosx, Windows, Unix
Data Formats: None
Tags: Eeg, Classification, Convex Optimization, Interior Point Method, Trace Norm

Search

Manage

Sort by

Filter by

Latest Thoughts

RSS Feed - Blog

RSS Feed - New Software

DAL 1.05

Logistic regression with dual spectral regularization 1.0