The performance of modern machine learning methods highly depends on their hyperparameter configurations. One simple way of selecting a configuration is to use default settings, often proposed along with the publication and implementation of a new algorithm. Those default values are usually chosen in an ad-hoc manner to work good enough on a wide variety of datasets. To address this problem, different automatic hyperparameter configuration algorithms have been proposed, which select an optimal configuration per dataset. This principled approach usually improves performance, but adds additional algorithmic complexity and computational costs to the training procedure. As an alternative to this, we propose learning a set of complementary default values from a large database of prior empirical results. Selecting an appropriate configuration on a new dataset then requires only a simple, efficient and embarrassingly parallel search over this set. We demonstrate the effectiveness and efficiency of the approach we propose in comparison to random search and Bayesian Optimization.

Understanding the influence of hyperparameters on the performance of a machine learning algorithm is an important scientific topic in itself and can help to improve automatic hyperparameter tuning procedures. Unfortunately, experimental meta data for this purpose is still rare. This paper presents a large, free and open dataset addressing this problem, containing results on 38 OpenML data sets, six different machine learning algorithms and many different hyperparameter configurations. Result where generated by an automated random sampling strategy, termed the OpenML Random Bot. Each algorithm was cross-validated up to 20.000 times per dataset with different hyperparameters settings, resulting in a meta dataset of around 2.5 million experiments overall.

The random forest algorithm (RF) has several hyperparameters that have to be set by the user, e.g., the number of observations drawn randomly for each tree and whether they are drawn with or without replacement, the number of variables drawn randomly for each split, the splitting rule, the minimum number of samples that a node must contain and the number of trees. In this paper, we first provide a literature review on the parameters' influence on the prediction performance and on variable importance measures, also considering interactions between hyperparameters. It is well known that in most cases RF works reasonably well with the default values of the hyperparameters specified in software packages. Nevertheless, tuning the hyperparameters can improve the performance of RF. In the second part of this paper, after a brief overview of tuning strategies we demonstrate the application of one of the most established tuning strategies, model-based optimization (MBO). To make it easier to use, we provide the tuneRanger R package that tunes RF with MBO automatically. In a benchmark study on several datasets, we compare the prediction performance and runtime of tuneRanger with other tuning implementations in R and RF with default hyperparameters.

Modern machine learning algorithms for classification or regression such as gradient boosting, random forest and neural networks involve a number of parameters that have to be fixed before running them. Such parameters are commonly denoted as hyperparameters in machine learning, a terminology we also adopt here. The term tuning parameter is also frequently used to denote parameters that should be carefully tuned, i.e. optimized with respect to performance. The users of these algorithms can use defaults of these hyperparameters that are specified in the employed software package, set them to alternative specific values or use a tuning strategy to choose them appropriately for the specific dataset at hand. In this context, we define tunability as the amount of performance gain that can be achieved by setting the considered hyperparameter to the best possible value instead of the default value. The goal of this paper is two-fold. Firstly, we formalize the problem of tuning from a statistical point of view and suggest general measures quantifying the tunability of hyperparameters of algorithms. Secondly, we conduct a large-scale benchmarking study based on 38 datasets from the OpenML platform (Vanschoren et al., 2013) using six of the most common machine learning algorithms for classification and regression and apply our measures to assess the tunability of their parameters. The results yield interesting insights into the investigated hyperparameters that in some cases allow general conclusions on their tunability. Our results may help users of the algorithms to decide whether it is worth to conduct a possibly time consuming tuning strategy, to focus on the most important hyperparameters and to chose adequate hyperparameter spaces for tuning.

The number of trees T in the random forest (RF) algorithm for supervised learning has to be set by the user. It is controversial whether T should simply be set to the largest computationally manageable value or whether a smaller T may in some cases be better. While the principle underlying bagging is that "more trees are better", in practice the classification error rate sometimes reaches a minimum before increasing again for increasing number of trees. The goal of this paper is four-fold: (i) providing theoretical results showing that the expected error rate may be a non-monotonous function of the number of trees and explaining under which circumstances this happens; (ii) providing theoretical results showing that such non-monotonous patterns cannot be observed for other performance measures such as the Brier score and the logarithmic loss (for classification) and the mean squared error (for regression); (iii) illustrating the extent of the problem through an application to a large number (n = 306) of datasets from the public database OpenML; (iv) finally arguing in favor of setting it to a computationally feasible large number, depending on convergence properties of the desired performance measure.

We implemented several multilabel classification algorithms in the machine learning package mlr. The implemented methods are binary relevance, classifier chains, nested stacking, dependent binary relevance and stacking, which can be used with any base learner that is accessible in mlr. Moreover, there is access to the multilabel classification versions of randomForestSRC and rFerns. All these methods can be easily compared by different implemented multilabel performance measures and resampling methods in the standardized mlr framework. In a benchmark experiment with several multilabel datasets, the performance of the different methods is evaluated.