jaehong31 / CGES

Combined Group and Exclusive Sparsity for Deep Neural Networks, ICML 2017
32 stars 9 forks source link

Question on proximal gradient update #5

Closed lizhenstat closed 4 years ago

lizhenstat commented 5 years ago

Hello, I have one question on equation (7) in the paper In the traditional proximal gradient descent method, the step size s in envolved in the equation

The above proximal operator involves the stepsize, however in equation(7) and equation(8) don't involve stepsize s, can you explain a little bit , thanks

lizhenstat commented 4 years ago

@jaehong-yoon93 Hi, I find the solution of (7) in the following link section 6.5 https://web.stanford.edu/~boyd/papers/pdf/prox_algs.pdf How do you prove equation(8)?

Thanks in advance