paper-with-me

Papers

Second-Order Sensitivity Analysis for Bilevel Optimization

2022-05-04 · Robert Dyro, Edward Schmerling, Nikos Arechiga, Marco Pavone

In this work we derive a second-order approach to bilevel optimization, a type of mathematical programming in which the solution to a parameterized optimization problem (the "lower" problem) is itself to be optimized (in the "upper" problem) as a function of the parameters. Many existing approaches to bilevel optimization employ first-order sensitivity analysis, based on the implicit function theorem (IFT), for the lower problem to derive a gradient of the lower problem solution with respect to its parameters; this IFT gradient is then used in a first-order optimization method for the upper problem. This paper extends this sensitivity analysis to provide second-order derivative information of the lower problem (which we call the IFT Hessian), enabling the usage of faster-converging second-order optimization methods at the upper level. Our analysis shows that (i) much of the computation already used to produce the IFT gradient can be reused for the IFT Hessian, (ii) errors bounds derived for the IFT gradient readily apply to the IFT Hessian, (iii) computing IFT Hessians can significantly reduce overall computation by extracting more information from each lower level solve. We corroborate our findings and demonstrate the broad range of applications of our method by applying it to problem instances of least squares hyperparameter auto-tuning, multi-class SVM auto-tuning, and inverse optimal control.

📄 PDF Abstract BibTeX arXiv:2205.02329

Code (3)

stanfordasl/second-ordersensitivityanalysisforbileveloptimization 공식 구현 jax
stanfordasl/sensitivity_jax 공식 구현 jax
stanfordasl/sensitivity_torch 공식 구현 pytorch

Tasks

Bilevel OptimizationSensitivity

Methods 이 논문이 사용한 방법론

SVM A Support Vector Machine, or SVM, is a non-parametric supervised learning model. For non-linear classification and regression, they utilise the kernel trick to map inputs…

Similar Papers 제목 키워드 기반

Fully Zeroth-Order Bilevel Programming via Gaussian Smoothing

2024-03-29 · Alireza Aghasi, Saeed Ghadimi

In this paper, we study and analyze zeroth-order stochastic approximation algorithms for solving bilvel problems, when neither the upper/lower objective values, nor their unbiased gradient estimates are available. In par…

Bilevel Optimization

Bridging Constraints and Stochasticity: A Fully First-Order Method for Stochastic Bilevel Optimization with Linear Constraints

2025-11-13 · Cac Phan, Kai Wang arxiv

This work provides the first finite-time convergence guarantees for linearly constrained stochastic bilevel optimization using only first-order methods, requiring solely gradient information without any Hessian computati…

Bilevel Optimization

Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions

2023-06-21 · Xuxing Chen, Tesi Xiao, Krishnakumar Balasubramanian

Stochastic Bilevel optimization usually involves minimizing an upper-level (UL) function that is dependent on the arg-min of a strongly-convex lower-level (LL) function. Several algorithms utilize Neumann series to appro…

Bilevel Optimization

On the Convergence Theory for Hessian-Free Bilevel Algorithms

2021-10-13 · Daouda Sow, Kaiyi Ji, Yingbin Liang

Bilevel optimization has arisen as a powerful tool in modern machine learning. However, due to the nested structure of bilevel optimization, even gradient-based methods require second-order derivative approximations via …

Bilevel OptimizationMeta-Learning

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