# Probabilistic Rollouts for Learning Curve Extrapolation Across Hyperparameter Settings

arXiv: https://arxiv.org/abs/1910.04522 · HTML: https://mlsanity.com/paper/1910.04522/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks](https://mlsanity.com/paper/2310.20447/) (2023)
- [In-Context Freeze-Thaw Bayesian Optimization for Hyperparameter Optimization](https://mlsanity.com/paper/2404.16795/) (2024)
- [NAS-Bench-x11 and the Power of Learning Curves](https://mlsanity.com/paper/2111.03602/) (2021)
- [Supervising the Multi-Fidelity Race of Hyperparameter Configurations](https://mlsanity.com/paper/2202.09774/) (2022)
- [Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation](https://mlsanity.com/paper/2412.15554/) (2024)
- [Cost-Sensitive Multi-Fidelity Bayesian Optimization with Transfer of Learning Curve Extrapolation](https://mlsanity.com/paper/2405.17918/) (2024)
- [Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning](https://mlsanity.com/paper/2510.21379/) (2025)
- [Configuration-to-Performance Scaling Law with Neural Ansatz](https://mlsanity.com/paper/2602.10300/) (2026)
- [Automatic model training under restrictive time constraints](https://mlsanity.com/paper/2104.10746/) (2021)
- [Bayesian Neural Scaling Law Extrapolation with Prior-Data Fitted Networks](https://mlsanity.com/paper/2505.23032/) (2025)
- [Gradient Flow Matching for Learning Update Dynamics in Neural Network Training](https://mlsanity.com/paper/2505.20221/) (2025)
- [A Risk Decomposition Framework for Pre-Hoc Fine-Tuning Prediction](https://mlsanity.com/paper/2606.17649/) (2026)

## Abstract (arXiv)

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.