l1 regularizations（更新待续）

L1 正则由于其能够产生稀疏解，所以广泛应用在工业届中。由于L1正则在0点的不可导性，所以如何求解L1正则就是一个问题。等有时间了，我会总结一些求解L1正则的方法。
先转载一些找到的资料，之后进行整理。
https://www.researchgate.net/post/What_is_the_solution_to_this_specific_type_of_Lasso_optimization_problem
https://www.quora.com/Which-optimization-algorithms-can-be-used-to-solve-a-LASSO-problem
https://www.quora.com/In-practice-for-large-data-sets-which-algorithms-are-recommended-to-solve-Lasso
https://math.stackexchange.com/questions/868934/what-numerical-methods-are-known-to-solve-l-1-regularized-quadratic-programmin
http://www.cs.cmu.edu/afs/cs/project/link-3/lafferty/www/ml-stat2/talks/YondaiKimGLasso-SLIDE-YD.pdf
（更新待续。）

转载于:https://www.cnblogs.com/dagger14/p/6774467.html