Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

2019/10/10 by Matilde Gargiani, Gargiani, Matilde, Aaron Klein +5 · 1 citation
Computer Science · #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Machine Learning and Data Classification

paper · pdf · doi:10.48550/arxiv.1910.04522

openalex publication_date 2019/10/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Freeze-Thaw Bayesian Optimization
• Auto-Encoding Variational Bayes
• Long Short-Term Memory
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Cited by

• Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning

Related

• Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks
• Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation
• Learning Curves for Analysis of Deep Networks
• Stochastic Hyperparameter Optimization through Hypernetworks
• Learning with Random Learning Rates