.png){kind=icon}
Return
Developing Lagrangian-Based Methods for Nonsmooth Nonconvex Optimization
.png){kind=icon}
PRE
AI
DOI：10.1287/moor.2024.0479.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we consider the minimization of a nonsmooth nonconvex objective function f (x) over a closed convex subset X of Rn, with additional nonsmooth nonconvex constraints c(x) = 0. We develop a unified framework for developing Lagrangian-based methods, which takes a single-step update to the primal variables by some subgradient methods in each iteration. These subgradient methods are embedded into our framework in the sense that they are incorporated as black-box updates to the primal variables. We prove that our proposed framework inherits the global convergence guarantees from these embedded subgradient methods under mild conditions. In addition, we show that our framework can be extended to solve constrained optimization problems with expectation constraints. Based on the proposed framework, we show that a wide range of existing stochastic subgradient methods, including proximal stochastic subgradient descent (SGD), proximal momentum SGD, and proximal adaptive moment estimation method (ADAM), can be embedded into Lagrangian-based methods. Preliminary numerical experiments on deep learning tasks illustrate that our proposed framework yields efficient variants of Lagrangian-based methods with convergence guarantees for nonsmooth nonconvex constrained optimization problems.
Keywords:
nonsmooth optimization
constrained optimization
Lagrangian-based methods
stochastic subgradient method
deep learning
Journal
M
IF:
1.9
Papers:
77
Citations:
0
Organization
View more organizations
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveShareSave
ShareSaveShareSave View more