Robust group fused lasso for multisample copy number variation detection under uncertainty

What is it about?

This paper presents in robust methodology to detect the Copy Number Variation in CGH array data. The proposed method is robust against non-Gaussian noises.

Featured Image

Why is it important?

CGH array are highly corrupted with large noises. The underlying assumption of various method is that the distribution of the noise is Gaussian. However, this assumption is violated in may real world applications. This paper presents a robust method which has no assumption on the distribution of noise and must have the same performance if the distribution of the noise is Gaussian or not.