A Complete Analysis of the l_1, p Group-Lasso

By Julia E. Vogt, Volker Roth. 2012

28 citations recorded by the source corpus.

The Group-Lasso is a well-known tool for joint regularization in machine learning methods. While the l_{1,2} and the l_{1,\infty} version have been studied in detail and efficient algorithms exist, there are still open questions regarding other l_{1,p} variants. We characterize conditions for solutions of the l_{1,p} Group-Lasso for all p-norms with 1 > 2.

Subfields: Computational Mechanics, Rheumatology, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Qiang Yang
2. Yu Zhang
3. Avrim Blum
4. Santosh Srinivas Vempala
5. Maria-Florina Balcan
6. David P. Woodruff

In Rheumatology

1. Qiang Yang
2. Avrim Blum
3. Santosh Srinivas Vempala
4. Maria-Florina Balcan

In Statistics and Probability

1. Qiang Yang
2. Avrim Blum
3. Santosh Srinivas Vempala
4. Maria-Florina Balcan
5. Yu Zhang
6. Blaine Nelson
7. L. Lov'asz

Citations in the corpus

• A Survey on Multi-Task Learning (2017, background): “For the optimization of problem (6), Vogt and Roth [25] propose an active set algorithm to solve the `p,1 norm regularization efficiently for arbitrary p.”
• Efficient Representations for Lifelong Learning and Autoencoding (2014, methodology): “There has also been work on applying the Group Lasso method to batch multi-task learning which solves a specific multi-task optimization problem [20].”