Goal-oriented sensitivity analysis of hyperparameters in deep learning

DOI10.1007/s10915-022-02083-4arXiv2207.06216OpenAlexW4200629985MaRDI QIDQ6159254

David Lugato, Gaël Poëtte, Pietro Marco Congedo, Paul Novello

Publication date: 20 June 2023

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2207.06216

zbMATH Keywords

sensitivity analysisinterpretabilityhyperparameter optimizationscientific machine learningHilbert-Schmidt independance criterion

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Multivariate analysis (62Hxx) Nonparametric inference (62Gxx)

Related Items (2)

Deterministic neural networks optimization from a continuous and energy point of view ⋮ Accelerating hypersonic reentry simulations using deep learning-based hybridization (with guarantees)

Cites Work

• Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
• Making best use of model evaluations to compute sensitivity indices
• Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis
• New sensitivity analysis subordinated to a contrast
• Integral Probability Metrics and Their Generating Classes of Functions
• Global sensitivity analysis with dependence measures
• Global Sensitivity Analysis for Optimization with Variable Selection
• Algorithmic Learning Theory
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Goal-oriented sensitivity analysis of hyperparameters in deep learning