paper-with-me

홈 › Papers

Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

2019-10-10 · Matilde Gargiani, Aaron Klein, Stefan Falkner, Frank Hutter

We propose probabilistic models that can extrapolate learning curves of iterative machine learning algorithms, such as stochastic gradient descent for training deep networks, based on training data with variable-length learning curves. We study instantiations of this framework based on random forests and Bayesian recurrent neural networks. Our experiments show that these models yield better predictions than state-of-the-art models from the hyperparameter optimization literature when extrapolating the performance of neural networks trained with different hyperparameter settings.

📄 PDF Abstract BibTeX arXiv:1910.04522

Code (1)

gmatilde/vdrnn 공식 구현 pytorch

Tasks

BIG-bench Machine LearningHyperparameter Optimization

Similar Papers 제목 키워드 기반

Tune My Adam, Please!

2025-08-27 · Theodoros Athanasiadis, Steven Adriaensen, Samuel Müller, Frank Hutter arxiv

The Adam optimizer remains one of the most widely used optimizers in deep learning, and effectively tuning its hyperparameters is key to optimizing performance. However, tuning can be tedious and costly. Freeze-thaw Baye…

Hyperparameter Optimization

Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation

2024-12-20 · Yanna Ding, Zijie Huang, Xiao Shou, Yihang Guo 외

Learning curve extrapolation predicts neural network performance from early training epochs and has been applied to accelerate AutoML, facilitating hyperparameter tuning and neural architecture search. However, existing …

AutoMLNeural Architecture Search

HAMLET -- A Learning Curve-Enabled Multi-Armed Bandit for Algorithm Selection

2020-01-30 · Mischa Schmidt, Julia Gastinger, Sébastien Nicolas, Anett Schülke

Automated algorithm selection and hyperparameter tuning facilitates the application of machine learning. Traditional multi-armed bandit strategies look to the history of observed rewards to identify the most promising ar…

BIG-bench Machine Learning

DEEP-BO for Hyperparameter Optimization of Deep Networks

2019-05-23 · NeurIPS19 under review 2019 5 · Hyunghun Cho, Yongjin Kim, Eunjung Lee, Daeyoung Choi 외

The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnor…

Bayesian OptimizationHyperparameter Optimization

Light curve completion and forecasting using fast and scalable Gaussian processes (MuyGPs)

2022-08-31 · Imène R. Goumiri, Alec M. Dunton, Amanda L. Muyskens, Benjamin W. Priest 외

Temporal variations of apparent magnitude, called light curves, are observational statistics of interest captured by telescopes over long periods of time. Light curves afford the exploration of Space Domain Awareness (SD…

Gaussian ProcessesPose EstimationTime SeriesTime Series Analysis