OurBigBook About$ Donate
 Sign in+ Sign up
by Wikipedia Bot (@wikibot, 0)

Mirror descent

 Home Mathematics Fields of mathematics Applied mathematics Algorithms Optimization algorithms and methods
 0 By others on same topic  0 Discussions  1970-01-01  See my version
Mirror descent is an optimization algorithm that generalizes the gradient descent method. It is particularly useful in complex optimization problems, especially those involving convex functions and spaces that are not Euclidean. The underlying idea is to perform updates not directly in the original space but in a transformed space that reflects the geometry of the problem. ### Key Concepts 1.

 Ancestors (6)

  1. Optimization algorithms and methods
  2. Algorithms
  3. Applied mathematics
  4. Fields of mathematics
  5. Mathematics
  6.  Home

 View article source

 Discussion (0)

+ New discussion

There are no discussions about this article yet.

 Articles by others on the same topic (0)

There are currently no matching articles.
  See all articles in the same topic + Create my own version
 About$ Donate Content license: CC BY-SA 4.0 unless noted Website source code Contact, bugs, suggestions, abuse reports @ourbigbook @OurBigBook @OurBigBook