# L21_sgdmet - Lecture 21 Subgradient Methods April 9 2007...

This preview shows pages 1–8. Sign up to view the full content.

Lecture 21: Subgradient Methods April 9, 2007

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Lecture 21 Outline Subgradients and Level Sets Subgradient Method Convergence and Convergence Rate Convex Optimization 1
Lecture 21 Subgradients and Level Sets A vector s is a subgradient of a convex function f : R n R at ˆ x dom f when subgradient inequality holds f ( z ) f x ) + s T ( z - ˆ x ) for all z dom f We have interpreted the subgradient inequality in terms of a hyperplane in R n +1 supporting the epigraph epi f at x, f x )) Convex Optimization 2

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Lecture 21 Projecting the hyperplane and the epigraph on the set { ( x, w ) | x R n , w = f x ) } The subgradient inequality can be interpreted in terms of a hyperplane in R n supporting the level set L γ ( f ) at ˆ x for γ = f x ) For z in the level set L f x ) ( f ) = { z | f ( z ) f x ) } , the subgradient inequality implies s T ( z - ˆ x ) 0 for all z L f x ) ( f ) and the inequality is tight at z = ˆ x . Convex Optimization 3
Lecture 21 Another Interpretation of Subgradients A subgradient of f at any ˆ x defines a hyperplane that cuts R n in two regions and one of them contains the level sets L γ ( f ) for all γ f x ) The optimal set X * lies entirely on one side of each such hyperplane Cutting-plane method can be interpreted as successively “reducing” the size of a region where the “optimal solutions” are located, by increasing the number of hyperplanes that “cut” the space R n Convex Optimization 4

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
Lecture 21 Subgradient Method Constrained Convex Minimization minimize f ( x ) subject to x X General Assumption The function f ( x ) is convex and dom f = R n The set X is nonempty closed and convex Subgradient Method Having the current iterate x k , a subgradient s k of f at x k , and a stepsize value α k > 0 , the next iterate is given by x k +1 = P X [ x k - α k s k ] Polyak 1969, Ermoliev 1969, Shor 1985 Convex Optimization 5
Lecture 21 Property “ensuring” that subgradient methods work Along the negative subgradient direction - s k , there is a range of stepsize (0 , ˜ a ) , such that

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern