Task-Oriented Convex Bilevel Optimization With Latent Feasibility

doi:10.1109/TIP.2022.3140607

Task-Oriented Convex Bilevel Optimization With Latent Feasibility

2022-01-01

6

OA

AI

DOI：10.1109/TIP.2022.3140607

Original

Original request for help

Save

Abstract

En 中文

This paper firstly proposes a convex bilevel optimization paradigm to formulate and optimize popular learning and vision problems in real-world scenarios. Different from conventional approaches, which directly design their iteration schemes based on given problem formulation, we introduce a task-oriented energy as our latent constraint which integrates richer task information. By explicitly re- characterizing the feasibility, we establish an efficient and flexible algorithmic framework to tackle convex models with both shrunken solution space and powerful auxiliary (based on domain knowledge and data distribution of the task). In theory, we present the convergence analysis of our latent feasibility re- characterization based numerical strategy. We also analyze the stability of the theoretical convergence under computational error perturbation. Extensive numerical experiments are conducted to verify our theoretical findings and evaluate the practical performance of our method on different applications.

Keywords:

Task analysis

Optimization

Convergence

Convex functions

Data models

Computational modeling

Standards

Convex optimization

latent constraint

global convergence

image processing

Task-Oriented Convex Bilevel Optimization With Latent Feasibility

Abstract

Journal

Organization