Algorithm Runtime Prediction: Methods and Evaluation (Extended Abstract)

By Frank Hutter, Lin Xu, Holger H. Hoos, Kevin Leyton-Brown. 2015

63 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Efficient Benchmarking of Hyperparameter Optimizers via Surrogates (2015, methodology): “We considered two different tree-based models, because random forest (RFs) have been shown to yield highquality predictions of algorithm performance data (Hutter et al. 2014) and because SMAC uses a RF.”
Initializing Bayesian Hyperparameter Optimization via Meta-Learning (2015, methodology): “In particular, SMAC uses random forests (Breiman 2001) modified to yield an uncertainty estimate (Hutter et al. 2014).”
Using Meta-Learning to Initialize Bayesian Optimization of Hyperparameters (2014, methodology): “In particular, SMAC uses random forests [6], modified to yield an uncertainty estimate [15].”
SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization (2021, background): “empirical performance models, EPMs (Hutter et al., 2014)), acquisition functions and intensification mechanisms to efficiently evaluate only parts of the true cost function.”
Learning to Optimize Tensor Programs (2018, methodology): “Previously, statistical cost models have been applied to optimize SAT solvers [17, 18].”
Surrogate Benchmarks for Hyperparameter Optimization (2014, methodology): “We evaluated three different tree-based models, because SMAC uses a random forest (RF), and because RFs have been shown to yield high-quality predictions of algorithm performance data [18].”
Efficient Parameter Importance Analysis via Ablation with Surrogates (2017, methodology): “As shown by Hutter et al. (2014b) and Eggensperger et al. (2015), random forest models are well suited as EPMs, but we cannot guarantee that their predictions are always accurate enough.”
Speeding Up Automatic Hyperparameter Optimization of Deep Neural Networks by Extrapolation of Learning Curves (2015, methodology): “, 2011], which uses random forests [Breiman, 2001] modified to yield an uncertainty estimate [Hutter et al., 2014]; and the Tree Parzen Estimator (TPE) [Bergstra et al.”
Warmstarting of Model-based Algorithm Configuration (2017, methodology): “…AC tasks from the conﬁgurable SAT solver challenge (Hutter et al. 2017), which are publicly available in the algorithm con-ﬁguration library (Hutter et al. 2014a To study warmstarting on different categories of instances, the AC tasks consider SAT instances from applications with a lot of…”