TY - GEN
T1 - Bundle methods for dual atomic pursuit
AU - Fan, Zhenan
AU - Sun, Yifan
AU - Friedlander, Michael P.
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11
Y1 - 2019/11
N2 - The aim of structured optimization is to assemble a solution, using a given set of (possibly uncountably infinite) atoms, to fit a model to data. A two-stage algorithm based on gauge duality and bundle method is proposed. The first stage discovers the optimal atomic support for the primal problem by solving a sequence of approximations of the dual problem using a bundle-type method. The second stage recovers the approximate primal solution using the atoms discovered in the first stage. The overall approach leads to implementable and efficient algorithms for large problems.
AB - The aim of structured optimization is to assemble a solution, using a given set of (possibly uncountably infinite) atoms, to fit a model to data. A two-stage algorithm based on gauge duality and bundle method is proposed. The first stage discovers the optimal atomic support for the primal problem by solving a sequence of approximations of the dual problem using a bundle-type method. The second stage recovers the approximate primal solution using the atoms discovered in the first stage. The overall approach leads to implementable and efficient algorithms for large problems.
UR - https://www.scopus.com/pages/publications/85083319255
U2 - 10.1109/IEEECONF44664.2019.9048711
DO - 10.1109/IEEECONF44664.2019.9048711
M3 - Conference contribution
AN - SCOPUS:85083319255
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 264
EP - 270
BT - Conference Record - 53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
A2 - Matthews, Michael B.
PB - IEEE Computer Society
T2 - 53rd Asilomar Conference on Circuits, Systems and Computers, ACSSC 2019
Y2 - 3 November 2019 through 6 November 2019
ER -