Image de couverture de livre

A Hessian-informed hyperparameter optimization for differential learning rate

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Xu, Shiyun, Bu, Zhiqi, Zhang, Yiliang, Barnett, Ian
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adaptive parameter-efficient fine-tuning via Hessian-informed subset selection
par: Xu, Shiyun, et autres
Publié: (2025)

Towards hyperparameter-free optimization with differential privacy
par: Bu, Zhiqi, et autres
Publié: (2025)

Gradient descent with generalized Newton's method
par: Bu, Zhiqi, et autres
Publié: (2024)

Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate
par: Bu, Zhiqi, et autres
Publié: (2026)

Be aware of overfitting by hyperparameter optimization!
par: Tetko, Igor V., et autres
Publié: (2024)

Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate
par: Bu, Zhiqi, et autres
Publié: (2024)

Scaling depth capacity via zero/one-layer model expansion
par: Bu, Zhiqi
Publié: (2025)

Beyond algorithm hyperparameters: on preprocessing hyperparameters and associated pitfalls in machine learning applications
par: Sauer, Christina, et autres
Publié: (2024)

An adaptively inexact first-order method for bilevel optimization with application to hyperparameter learning
par: Salehi, Mohammad Sadegh, et autres
Publié: (2023)

Bilevel optimization for learning hyperparameters: Application to solving PDEs and inverse problems with Gaussian processes
par: Nelsen, Nicholas H., et autres
Publié: (2025)

How far away are truly hyperparameter-free learning algorithms?
par: Kasimbeg, Priya, et autres
Publié: (2025)

Two-step hyperparameter optimization method: Accelerating hyperparameter search by using a fraction of a training dataset
par: Yu, Sungduk, et autres
Publié: (2023)

Fuzzy hyperparameters update in a second order optimization
par: Bensadok, Abdelaziz, et autres
Publié: (2024)

Relax and penalize: a new bilevel approach to mixed-binary hyperparameter optimization
par: Venturini, Sara, et autres
Publié: (2023)

Hessian-informed machine learning interatomic potential towards bridging theory and experiments
par: Yin, Bangchen, et autres
Publié: (2026)

Bayesian autoregression to optimize temporal Matérn kernel Gaussian process hyperparameters
par: Kouw, Wouter M.
Publié: (2025)

Application-oriented automatic hyperparameter optimization for spiking neural network prototyping
par: Fra, Vittorio
Publié: (2025)

An algorithmic framework for the optimization of deep neural networks architectures and hyperparameters
par: Keisler, Julie, et autres
Publié: (2023)

Regularized boosting with an increasing coefficient magnitude stop criterion as meta-learner in hyperparameter optimization stacking ensemble
par: Fdez-Díaz, Laura, et autres
Publié: (2024)

Offline-to-online hyperparameter transfer for stochastic bandits
par: Sharma, Dravyansh, et autres
Publié: (2025)

Effect of hyperparameters on variable selection in random forests
par: Fouodo, Cesaire J. K., et autres
Publié: (2023)

Selecting time-series hyperparameters with the artificial jackknife
par: Pellegrino, Filippo
Publié: (2020)

Calibrating dimension reduction hyperparameters in the presence of noise
par: Lin, Justin, et autres
Publié: (2023)

DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
par: Zhang, Xinwei, et autres
Publié: (2024)

A two-step sequential approach for hyperparameter selection in finite context models
par: Contente, José, et autres
Publié: (2026)

Adaptive multi-fidelity optimization with fast learning rates
par: Fiegel, Come, et autres
Publié: (2026)

FORML: A Riemannian Hessian-free Method for Meta-learning on Stiefel Manifolds
par: Tabealhojeh, Hadi, et autres
Publié: (2024)

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
par: Zhang, Xinwei, et autres
Publié: (2023)

Newton-CG methods for nonconvex unconstrained optimization with Hölder continuous Hessian
par: He, Chuan, et autres
Publié: (2023)

Sharp Trade-Offs in High-Dimensional Inference via 2-Level SLOPE
par: Bu, Zhiqi, et autres
Publié: (2025)

Pre-training Differentially Private Models with Limited Public Data
par: Bu, Zhiqi, et autres
Publié: (2024)

What do near-optimal learning rate schedules look like?
par: Naganuma, Hiroki, et autres
Publié: (2026)

A Confidence Interval for the $\ell_2$ Expected Calibration Error
par: Sun, Yan, et autres
Publié: (2024)

Globally aware optimization with resurgence
par: Bu, Wei
Publié: (2025)

Better Trees: An empirical study on hyperparameter tuning of classification decision tree induction algorithms
par: Mantovani, Rafael Gomes, et autres
Publié: (2018)

GNNAS-Dock: Budget Aware Algorithm Selection with Graph Neural Networks for Molecular Docking
par: Yuan, Yiliang, et autres
Publié: (2024)

ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction
par: Lyu, Jiacheng, et autres
Publié: (2026)

Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 Experiments
par: Li, Xiaoyi
Publié: (2026)

$μ$pscaling small models: Principled warm starts and hyperparameter transfer
par: Ma, Yuxin, et autres
Publié: (2026)

An Empirical Study of Scaling Laws for Transfer
par: Barnett, Matthew
Publié: (2024)