paper-with-me

Papers

Enhancing Hypergradients Estimation: A Study of Preconditioning and Reparameterization

2024-02-26 · Zhenzhang Ye, Gabriel Peyré, Daniel Cremers, Pierre Ablin

Bilevel optimization aims to optimize an outer objective function that depends on the solution to an inner optimization problem. It is routinely used in Machine Learning, notably for hyperparameter tuning. The conventional method to compute the so-called hypergradient of the outer problem is to use the Implicit Function Theorem (IFT). As a function of the error of the inner problem resolution, we study the error of the IFT method. We analyze two strategies to reduce this error: preconditioning the IFT formula and reparameterizing the inner problem. We give a detailed account of the impact of these two modifications on the error, highlighting the role played by higher-order derivatives of the functionals at stake. Our theoretical findings explain when super efficiency, namely reaching an error on the hypergradient that depends quadratically on the error on the inner problem, is achievable and compare the two approaches when this is impossible. Numerical evaluations on hyperparameter tuning for regression problems substantiate our theoretical findings.

📄 PDF Abstract BibTeX arXiv:2402.16748

Code (1)

zhenzhang-ye/enhance_hypergradient 공식 구현 jax

Tasks

Bilevel Optimization

Similar Papers 제목 키워드 기반

Glocal Hypergradient Estimation with Koopman Operator

2024-02-05 · Ryuichiro Hataya, Yoshinobu Kawahara

Gradient-based hyperparameter optimization methods update hyperparameters using hypergradients, gradients of a meta criterion with respect to hyperparameters. Previous research used two distinct update strategies: optimi…

Hyperparameter Optimization

Preconditioned Robust Neural Posterior Estimation for Misspecified Simulators

2026-02-20 · Ryan P. Kelly, David T. Frazier, David J. Warne, Christopher C. Drovandi arxiv

Simulation-based inference (SBI) enables parameter estimation for complex stochastic models with intractable likelihoods when model simulation is feasible. Neural posterior estimation (NPE) is a popular SBI approach that…

Improving Implicit Regularization of SGD with Preconditioning for Least Square Problems

2024-03-13 · Junwei Su, Difan Zou, Chuan Wu

Stochastic gradient descent (SGD) exhibits strong algorithmic regularization effects in practice and plays an important role in the generalization of modern machine learning. However, prior research has revealed instance…

regression

Enhancing Pure-Pixel Identification Performance via Preconditioning

2014-06-20 · Nicolas Gillis, Wing-Kin Ma

In this paper, we analyze different preconditionings designed to enhance robustness of pure-pixel search algorithms, which are used for blind hyperspectral unmixing and which are equivalent to near-separable nonnegative …

Hyperspectral UnmixingSingle Particle Analysis

On Quantum Natural Policy Gradients

2024-01-16 · André Sequeira, Luis Paulo Santos, Luis Soares Barbosa

This research delves into the role of the quantum Fisher Information Matrix (FIM) in enhancing the performance of Parameterized Quantum Circuit (PQC)-based reinforcement learning agents. While previous studies have highl…

Multi-Armed Banditsreinforcement-learningReinforcement Learning