paper-with-me

홈 › Papers

An Adaptively Inexact Method for Bilevel Learning Using Primal-Dual Style Differentiation

2024-12-09 · Lea Bogensperger, Matthias J. Ehrhardt, Thomas Pock, Mohammad Sadegh Salehi, Hok Shing Wong

We consider a bilevel learning framework for learning linear operators. In this framework, the learnable parameters are optimized via a loss function that also depends on the minimizer of a convex optimization problem (denoted lower-level problem). We utilize an iterative algorithm called `piggyback' to compute the gradient of the loss and minimizer of the lower-level problem. Given that the lower-level problem is solved numerically, the loss function and thus its gradient can only be computed inexactly. To estimate the accuracy of the computed hypergradient, we derive an a-posteriori error bound, which provides guides for setting the tolerance for the lower-level problem, as well as the piggyback algorithm. To efficiently solve the upper-level optimization, we also propose an adaptive method for choosing a suitable step-size. To illustrate the proposed method, we consider a few learned regularizer problems, such as training an input-convex neural network.

📄 PDF Abstract BibTeX arXiv:2412.06436

Code (1)

MohammadSadeghSalehi/Analytical-Deep-Priors pytorch

Similar Papers 제목 키워드 기반

Inexact Primal-Dual Gradient Projection Methods for Nonlinear Optimization on Convex Set

2019-11-18 · Fan Zhang, Hao Wang, Jiashan Wang, Kai Yang

In this paper, we propose a novel primal-dual inexact gradient projection method for nonlinear optimization problems with convex-set constraint. This method only needs inexact computation of the projections onto the conv…

Inexact bilevel stochastic gradient methods for constrained and unconstrained lower-level problems

2021-10-01 · Tommaso Giovannelli, Griffin Dean Kent, Luis Nunes Vicente

Two-level stochastic optimization formulations have become instrumental in a number of machine learning contexts such as continual learning, neural architecture search, adversarial learning, and hyperparameter tuning. Pr…

BIG-bench Machine LearningBilevel OptimizationContinual LearningNeural Architecture Search+1

A Primal-Dual Approach to Bilevel Optimization with Multiple Inner Minima

2022-03-01 · Daouda Sow, Kaiyi Ji, Ziwei Guan, Yingbin Liang

Bilevel optimization has found extensive applications in modern machine learning problems such as hyperparameter optimization, neural architecture search, meta-learning, etc. While bilevel problems with a unique inner mi…

Bilevel OptimizationHyperparameter OptimizationMeta-LearningNeural Architecture Search

An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning

2023-08-19 · Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts, Matthias J. Ehrhardt

Various tasks in data science are modeled utilizing the variational regularization approach, where manually selecting regularization parameters presents a challenge. The difficulty gets exacerbated when employing regular…

Bilevel OptimizationDenoising

Bilevel Learning with Inexact Stochastic Gradients

2024-12-16 · Mohammad Sadegh Salehi, Subhadip Mukherjee, Lindon Roberts, Matthias J. Ehrhardt

Bilevel learning has gained prominence in machine learning, inverse problems, and imaging applications, including hyperparameter optimization, learning data-adaptive regularizers, and optimizing forward operators. The la…

Bilevel OptimizationDeblurringDenoisingHyperparameter Optimization+2