paper-with-me

홈 › Papers

Supervising the Multi-Fidelity Race of Hyperparameter Configurations

2022-02-20 · Martin Wistuba, Arlind Kadra, Josif Grabocka

Multi-fidelity (gray-box) hyperparameter optimization techniques (HPO) have recently emerged as a promising direction for tuning Deep Learning methods. However, existing methods suffer from a sub-optimal allocation of the HPO budget to the hyperparameter configurations. In this work, we introduce DyHPO, a Bayesian Optimization method that learns to decide which hyperparameter configuration to train further in a dynamic race among all feasible configurations. We propose a new deep kernel for Gaussian Processes that embeds the learning curve dynamics, and an acquisition function that incorporates multi-budget information. We demonstrate the significant superiority of DyHPO against state-of-the-art hyperparameter optimization methods through large-scale experiments comprising 50 datasets (Tabular, Image, NLP) and diverse architectures (MLP, CNN/NAS, RNN).

📄 PDF Abstract BibTeX arXiv:2202.09774

Code (1)

releaunifreiburg/dyhpo 공식 구현 pytorch

Tasks

Bayesian OptimizationGaussian ProcessesHyperparameter Optimization

Similar Papers 제목 키워드 기반

Improving Multi-fidelity Optimization with a Recurring Learning Rate for Hyperparameter Tuning

2022-09-26 · Hyunjae Lee, Gihyeon Lee, Junhwan Kim, Sungjun Cho 외

Despite the evolution of Convolutional Neural Networks (CNNs), their performance is surprisingly dependent on the choice of hyperparameters. However, it remains challenging to efficiently explore large hyperparameter sea…

image-classificationImage ClassificationTransfer Learning

A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation

2025-09-02 · Seohyun Kim, Junyoung Lee, Jongho Park, Jinhyung Koo 외 arxiv

We propose DiTTO, a novel diffusion-based framework for generating realistic, precisely configurable, and diverse multi-device storage traces. Leveraging advanced diffusion techniques, DiTTO enables the synthesis of high…

Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuning

2019-03-12 · Jian Wu, Saul Toscano-Palmerin, Peter I. Frazier, Andrew Gordon Wilson

Bayesian optimization is popular for optimizing time-consuming black-box objectives. Nonetheless, for hyperparameter tuning in deep neural networks, the time required to evaluate the validation error for even a few hyper…

Bayesian Optimization

Efficient Hyperparameter Optimization for LLM Reinforcement Learning

2026-06-02 · Minping Chen, Bowen Xiao, Du Liang, Chuxuan Zeng 외 arxiv

Reinforcement learning (RL) for large language models (LLMs) is highly sensitive to hyperparameter configurations, making hyperparameter optimization (HPO) essential yet computationally expensive. Existing multi-fidelity…

Hyperparameter OptimizationComputational EfficiencyReinforcement Learning

Physics-Informed CoKriging: A Gaussian-Process-Regression-Based Multifidelity Method for Data-Model Convergence

2018-11-24 · Xiu Yang, David Barajas-Solano, Guzel Tartakovsky, Alexandre Tartakovsky

In this work, we propose a new Gaussian process regression (GPR)-based multifidelity method: physics-informed CoKriging (CoPhIK). In CoKriging-based multifidelity methods, the quantities of interest are modeled as linear…

Active LearningGaussian ProcessesGPRregression