Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework
Video presentation by André Biedenkapp for our paper "Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework" which was presented at ECAI2020.
Abstract:
The performance of many algorithms ... in the fields of hard combinatorial problem solving, machine learning or AI in general depends on parameter tuning. Automated methods have been proposed to alleviate users from the tedious and error-prone task of manually searching for performance-optimized configurations across a set of problem instances. However, there is still a lot of untapped potential through adjusting an algorithm’s parameters online since different parameter values can be optimal at different stages of the algorithm. Prior work showed that reinforcement learning is an effective approach to learn policies for online adjustments of algorithm parameters in a data-driven way. We extend that approach by formulating the resulting dynamic algorithm configuration as a contextual MDP, such that RL not only learns a policy for a single instance, but across a set of instances. To lay the foundation for studying dynamic algorithm configuration with RL in a controlled setting, we propose white-box benchmarks covering major aspects that make dynamic algorithm configuration a hard problem in practice and study the performance of various types of configuration strategies for them. On these white-box benchmarks, we show that (i) RL is a robust candidate for learning configuration policies, outperforming standard parameter optimization approaches, such as classical algorithm configuration; (ii) based on function approximation, RL agents can learn to generalize to new types of instances; and (iii) self-paced learning can substantially improve the performance by selecting a useful sequence of training instances automatically.[+] Show More
Abstract:
The performance of many algorithms ... in the fields of hard combinatorial problem solving, machine learning or AI in general depends on parameter tuning. Automated methods have been proposed to alleviate users from the tedious and error-prone task of manually searching for performance-optimized configurations across a set of problem instances. However, there is still a lot of untapped potential through adjusting an algorithm’s parameters online since different parameter values can be optimal at different stages of the algorithm. Prior work showed that reinforcement learning is an effective approach to learn policies for online adjustments of algorithm parameters in a data-driven way. We extend that approach by formulating the resulting dynamic algorithm configuration as a contextual MDP, such that RL not only learns a policy for a single instance, but across a set of instances. To lay the foundation for studying dynamic algorithm configuration with RL in a controlled setting, we propose white-box benchmarks covering major aspects that make dynamic algorithm configuration a hard problem in practice and study the performance of various types of configuration strategies for them. On these white-box benchmarks, we show that (i) RL is a robust candidate for learning configuration policies, outperforming standard parameter optimization approaches, such as classical algorithm configuration; (ii) based on function approximation, RL agents can learn to generalize to new types of instances; and (iii) self-paced learning can substantially improve the performance by selecting a useful sequence of training instances automatically.[+] Show More
Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework
Video presentation by André Biedenkapp for our paper "Dynamic [...]
Tutorial on Algorithm Configuration (PPSN'20)
Website: https://www.automl.org/events/tutorial_ac_2020/ Slides: [...]
Getting the most out of your planner(s): from static to dynamic algorithm configuration
Invited Talk at ICAPS 2020 by Frank Hutter
Learning Synthetic Environments for RL with Evolution Strategies (AAAI 2021 Meta-Learning Workshop)
This is the recording of our contributed talk at the AAAI 2021 [...]
HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPO
https://arxiv.org/abs/2109.06716 To achieve peak predictive [...]
piBO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization
by Carl Hvarfner, Danny Stoll, Artur Souza, Marius Lindauer, Frank [...]