• Publications
  • Influence
Algorithm Selection and Scheduling
This work proposes various static as well as dynamic scheduling strategies, and demonstrates that in comparison to pure algorithm selection, this novel combination of scheduling and solver selection can significantly boost performance. Expand
Model-Based Genetic Algorithms for Algorithm Configuration
A new model designed specifically for the task of predicting high-performance regions in the parameter space is introduced, and the ideas of genetic engineering of offspring as well as sexual selection of parents are introduced. Expand
Algorithm Portfolios Based on Cost-Sensitive Hierarchical Clustering
A new classifier that selects solvers based on a cost-sensitive hierarchical clustering model is devised that outperforms the most effective portfolio builders to date. Expand
Adaptive data augmentation for image classification
A new automatic and adaptive algorithm for choosing the transformations of the samples used in data augmentation, where for each sample, the main idea is to seek a small transformation that yields maximal classification loss on the transformed sample. Expand
Learning to Solve QBF
We present a novel approach to solving Quantified Boolean Formulas (QBF) that combines a search-based QBF solver with marhine learning techniques. We show how classification methods can be used toExpand
Experiments with Massively Parallel Constraint Solving
This paper proposes techniques that are simple to apply and show empirically that they scale surprisingly well, and establishes a performance baseline for parallel constraint solving technologies against which more sophisticated parallel algorithms need to compete in the future. Expand
Using SAT in QBF
This paper presents a technique for alleviating some of the complexity in QBF by utilizing an order unconstrained SAT solver during QBF solving by developing methods that allow information obtained from each solver to be used to improve the performance of the other. Expand
Learning Feature Engineering for Classification
This work presents a novel technique, called Learning Feature Engineering (LFE), for automating feature engineering in classification tasks, based on learning the effectiveness of applying a transformation on numerical features, from past feature engineering experiences. Expand
Feature Engineering for Predictive Modeling using Reinforcement Learning
This work presents a new framework to automate feature engineering, based on performance driven exploration of a transformation graph, which systematically and compactly enumerates the space of given options. Expand
Guiding Combinatorial Optimization with UCT
We propose a new approach for search tree exploration in the context of combinatorial optimization, specifically Mixed Integer Programming (MIP), that is based on UCT, an algorithm for theExpand