The task of algorithm selection involves choosing an algorithm from a set of algorithms on a per-instance basis in order to exploit the varying performance of algorithms over a set of instances. The algorithm selection problem is attracting increasing attention from researchers and practitioners in AI. Years of fruitful applications in a number of domains have resulted in a large amount of data, but the community lacks a standard format or repository for this data. This situation makes it difficult to share and compare different approaches effectively, as is done in other, more established fields. It also unnecessarily hinders new researchers who want to work in this area. To address this problem, we introduce a standardized format for representing algorithm selection scenarios and a repository that contains a growing number of data sets from the literature. Our format has been designed to be able to express a wide variety of different scenarios. To demonstrate the breadth and power of our platform, we describe a study that builds and evaluates algorithm selection models through a common interface. The results display the potential of algorithm selection to achieve significant performance improvements across a broad range of problems and algorithms.• A human-readable README file explains the origin and meaning of the scenario, as well as the process of data generation.Optional Data.• The feature costs file contains the costs of the feature groups, i.e., sets of features computed together.• The ground truth file specifies information on the instances and their respective solutions (e.g., SAT or UNSAT).• The literature references file in BibTeX format includes information on the context in which the data set was generated and previous studies in which it was used. Algorithm Selection Scenarios Provided in ASlib Release 2.0The set of algorithm selection scenarios in release version 2.0 of our library, shown in Table 2, has been assembled to represent a diverse set of selection problem settings that covers a wide range of problem domains, types of algorithms, 7 http://www.satcompetition.org/ 8 http://www.qbflib.org/index_eval.php 9 http://qbf.satisfiability.org/gallery/

Recent advances in AutoML have led to automated tools that can compete with machine learning experts on supervised learning tasks. In this work, we present two versions of Auto-Net, which provide automatically-tuned deep neural networks without any human intervention. The first version, Auto-Net 1.0, builds upon ideas from the competition-winning system Auto-sklearn by using the Bayesian Optimization method SMAC and uses Lasagne as the underlying deep learning (DL) library. The more recent Auto-Net 2.0 builds upon a recent combination of Bayesian Optimization and HyperBand, called BOHB, and uses PyTorch as DL library. To the best of our knowledge, Auto-Net 1.0 was the first automatically-tuned neural network to win competition datasets against human experts (as part of the first AutoML challenge). Further empirical results show that ensembling Auto-Net 1.0 with Auto-sklearn can perform better than either approach alone, and that Auto-Net 2.0 can perform better yet.

No abstract

Most machine learning algorithms are configured by a set of hyperparameters whose values must be carefully chosen and which often considerably impact performance. To avoid a time-consuming and irreproducible manual process of trial-anderror to find well-performing hyperparameter configurations, various automatic hyperparameter optimization (HPO) methods-for example, based on resampling error estimation for supervised machine learning-can be employed. After introducing HPO from a general perspective, this paper reviews important HPO methods, from simple techniques such as grid or random search to more advanced methods like evolution strategies, Bayesian optimization, Hyperband, and racing. This work gives practical recommendations regarding important choices to be made when conducting HPO, including the HPO algorithms themselves, performance evaluation, how to combine HPO with machine learning pipelines, runtime improvements, and parallelization.

It is well known that different solution strategies work well for different types of instances of hard combinatorial problems. As a consequence, most solvers for the propositional satisfiability problem (SAT) expose parameters that allow them to be customized to a particular family of instances. In the international SAT competition series, these parameters are ignored: solvers are run using a single default parameter setting (supplied by the authors) for all benchmark instances in a given track. While this competition format rewards solvers with robust default settings, it does not reflect the situation faced by a practitioner who only cares about performance on one particular application and can invest some time into tuning solver parameters for this application. The new Configurable SAT Solver Competition (CSSC) compares solvers in this latter setting, scoring each solver by the performance it achieved after a fully automated configuration step. This article describes the CSSC in more detail, and reports the results obtained in its two instantiations so far, CSSC 2013 and 2014.