MathOverflow Asked by user263322 on January 1, 2021

Consider the optimization problem

$$ minlimits_{x, alpha} sum_i alpha_i f_i(x) + g(alpha). $$

I solved the above problem by alternating fixing $x$ solve for $alpha$ and vice versa. When $x$ is fixed, the corresponding optimization with variables $alpha$ is convex and has a closed form solution. When $alpha$ is fixed, the problem is non-convex and it is solved by a gradient descent algorithm (called this problem OP2).

My question is does the above alternative scheme converge (a local optimum) given than OP2 converges to a local optimum. If it is not do you know in which conditions does alternative scheme converge?

Thanks

Get help from others!

Recent Questions

- How can I transform graph image into a tikzpicture LaTeX code?
- How Do I Get The Ifruit App Off Of Gta 5 / Grand Theft Auto 5
- Iv’e designed a space elevator using a series of lasers. do you know anybody i could submit the designs too that could manufacture the concept and put it to use
- Need help finding a book. Female OP protagonist, magic
- Why is the WWF pending games (“Your turn”) area replaced w/ a column of “Bonus & Reward”gift boxes?

Recent Answers

- haakon.io on Why fry rice before boiling?
- Joshua Engel on Why fry rice before boiling?
- Peter Machado on Why fry rice before boiling?
- Jon Church on Why fry rice before boiling?
- Lex on Does Google Analytics track 404 page responses as valid page views?

© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP