Literature Overview

@inproceedings{biedenkapp-gecco22a,

title = {Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration},

author = {André Biedenkapp and Nguyen Dang and Martin S. Krejca and Frank Hutter and Carola Doerr},

url = {https://arxiv.org/abs/2202.03259},

year  = {2022},

date = {2022-07-09},

urldate = {2022-07-09},

booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'22)},

journal = {arXiv:2202.03259 [cs.NE]},

abstract = {It has long been observed that the performance of evolutionary algorithms and other randomized search heuristics can benefit from a non-static choice of the parameters that steer their optimization behavior. Mechanisms that identify suitable configurations on the fly ("parameter control") or via a dedicated training process ("dynamic algorithm configuration") are therefore an important component of modern evolutionary computation frameworks. Several approaches to address the dynamic parameter setting problem exist, but we barely understand which ones to prefer for which applications. As in classical benchmarking, problem collections with a known ground truth can offer very meaningful insights in this context. Unfortunately, settings with well-understood control policies are very rare.

One of the few exceptions for which we know which parameter settings minimize the expected runtime is the LeadingOnes problem. We extend this benchmark by analyzing optimal control policies that can select the parameters only from a given portfolio of possible values. This also allows us to compute optimal parameter portfolios of a given size. We demonstrate the usefulness of our benchmarks by analyzing the behavior of the DDQN reinforcement learning approach for dynamic algorithm configuration. },

keywords = {},

pubstate = {forthcoming},

tppubtype = {inproceedings}

}

@inproceedings{getzelman-acml21a,

title = {Learning to Switch Optimizers for Quadratic Programming},

author = {Getzelman, Grant and Balaprakash, Prasanna},

editor = {Balasubramanian, Vineeth N. and Tsang, Ivor},

url = {https://proceedings.mlr.press/v157/getzelman21a.html},

year  = {2021},

date = {2021-11-17},

booktitle = {Proceedings of The 13th Asian Conference on Machine Learning},

volume = {157},

pages = {1553--1568},

publisher = {PMLR},

series = {Proceedings of Machine Learning Research},

abstract = {Quadratic programming (QP) seeks to solve optimization problems involving quadratic functions that can include complex boundary constraints. QP in the unrestricted form is $mathcal{NP}$-hard; but when restricted to the convex case, it becomes tractable. Active set and interior point methods are used to solve convex problems, and in the nonconvex case various heuristics or relaxations are used to produce high-quality solutions in finite time. Learning to optimize (L2O) is an emerging approach to design solvers for optimization problems. We develop an L2O approach that uses reinforcement learning to learn a stochastic policy to switch between pre-existing optimization algorithms to solve QP problem instances. In particular, our agent switches between three simple optimizers: Adam, gradient descent, and random search. Our experiments show that the learned optimizer minimizes quadratic functions faster and finds better-quality solutions in the long term than do any of the possible optimizers switched between. We also compare our solver with the standard QP algorithms in MATLAB and find better performance in fewer function evaluations.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{malashin-acm21,

title = {Sparsely Ensembled Convolutional Neural Network Classifiers via Reinforcement Learning},

author = {Olegovich Malashin, Roman},

url = {https://dl.acm.org/doi/10.1145/3468891.3468906

https://arxiv.org/abs/2102.03921},

doi = {10.1145/3468891.3468906},

isbn = {9781450389402},

year  = {2021},

date = {2021-09-06},

booktitle = {2021 6th International Conference on Machine Learning Technologies},

pages = {102–110},

series = {ICMLT 2021},

abstract = {We consider convolutional neural network (CNN) ensemble learning with the objective function inspired by the least action principle; it includes resource consumption component. We teach an agent to perceive images through the set of pre-trained classifiers and want the resulting dynamically configured system to unfold the computational graph with the trajectory that refers to the minimal number of operations and maximal expected accuracy. The proposed agent's architecture implicitly approximates the required classifier selection function with the help of reinforcement learning. Our experimental results prove, that if the agent exploits the dynamic (and context-dependent) structure of computations, it outperforms conventional ensemble learning.},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{nguyen-ial21a,

title = {MetaREVEAL: RL-based Meta-learning from Learning Curves},

author = {Manh Hung Nguyen and Nathan Grinsztajn and Isabelle Guyon and Lisheng Sun-Hosoy},

url = {https://hal.inria.fr/hal-03502358v2/document},

year  = {2021},

date = {2021-09-01},

urldate = {2021-09-01},

booktitle = {Workshop on Interactive Adaptive Learning co-located with European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021)},

abstract = {This paper addresses a cornerstone of Automated Machine Learning: the problem of rapidly uncovering which machine learning algorithm performs best on a new dataset. Our approach leverages performances of such algorithms on datasets to which they have been previously exposed, i.e., implementing a form of meta-learning. More specifically, the problem is cast as a REVEAL Reinforcement Learning (RL) game: the meta-learning problem is wrapped into a RL environment in which an agent can start, pause, or resume training various machine learning algorithms to progressively “reveal” their learning curves. The learned policy is then applied to quickly uncover the best algorithm on a new dataset. While other similar approaches, such as Freeze-Thaw, were proposed in the past, using Bayesian optimization, our methodology is, to the best of our knowledge, the first that trains a RL agent to do this task on previous datasets. Using real and artificial data, we show that our new RL-based meta-learning paradigm outperforms Free-Thaw and other baseline methods, with respect to the Area under the Learning curve metric, a form of evaluation of Any-time learning (i.e., the capability of interrupting the algorithm at any time while obtaining good performance).},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{speck-icaps21b,

title = {Learning Heuristic Selection with Dynamic Algorithm Configuration},

author = {D Speck and A Biedenkapp and F Hutter and R Mattmüller and M Lindauer},

editor = {H H Zhuo and Q Yang and M Do and R Goldman and S Biundo and M Katz},

url = {https://ojs.aaai.org/index.php/ICAPS/article/view/16008},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the 31st International Conference on Automated Planning and Scheduling (ICAPS'21)},

pages = {597--605},

publisher = {AAAI},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{eimer-ijcai21,

title = {DACBench: A Benchmark Library for Dynamic Algorithm Configuration},

author = {T Eimer and A Biedenkapp and M Reimer and S Adriaensen and F Hutter and M Lindauer},

url = {https://ml.informatik.uni-freiburg.de/papers/21-IJCAI-DACBench.pdf},

year  = {2021},

date = {2021-01-01},

booktitle = {Proceedings of the Thirtieth International Joint Conference on 

 Artificial Intelligence (IJCAI'21)},

publisher = {ijcai.org},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{<LineBreak>bhatia-icaps21,

title = {Tuning the Hyperparameters of Anytime Planning: A Deep Reinforcement Learning Approach},

author = {Abhinav Bhatia and Justin Svegliato and Shlomo Zilberstein},

url = {https://openreview.net/forum?id=c7hpFp_eRCo},

year  = {2021},

date = {2021-01-01},

urldate = {2021-01-01},

booktitle = {ICAPS 2021 Workshop on Heuristics and Search for Domain-independent Planning},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gomoluch-icaps20b,

title = {Learning Neural Search Policies for Classical Planning},

author = {Pawel Gomoluch and Dalal Alrajeh and Alessandra Russo and Antonio Bucchiarone},

url = {https://icaps20.icaps-conference.org/paper191.html},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Proceedings of the International Conference on Automated Planning and Scheduling},

volume = {30},

pages = {522--530},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{shala-ppsn20b,

title = {Learning Step-Size Adaptation in CMA-ES},

author = {G Shala and A Biedenkapp and N Awad and S Adriaensen and M Lindauer and F Hutter},

url = {https://ml.informatik.uni-freiburg.de/papers/20-PPSN-LTO-CMA.pdf},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

booktitle = {Proceedings of the Sixteenth International Conference on Parallel Problem Solving from Nature (PPSN'20)},

pages = {691--706},

publisher = {Springer},

series = {Lecture Notes in Computer Science},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sae-dan-gecco20b,

title = {Time-Dependent Automatic Parameter Configuration of a Local Search Algorithm},

author = {Weerapan Sae-Dan and Marie-Eléonore Kessaci and Nadarajen Veerapen and Laetitia Jourdan},

url = {https://doi.org/10.1145/3377929.3398107},

doi = {10.1145/3377929.3398107},

isbn = {9781450371278},

year  = {2020},

date = {2020-01-01},

booktitle = {Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion},

pages = {1898–1905},

publisher = {Association for Computing Machinery},

address = {Cancún, Mexico},

series = {GECCO '20},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sharma-gecco19b,

title = {Deep reinforcement learning based parameter control in differential evolution},

author = {Mudita Sharma and Alexandros Komninos and Manuel López-Ibá{~n}ez and Dimitar Kazakov},

editor = {A Auger and St T ü},

url = {https://dl.acm.org/doi/10.1145/3321707.3321813},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'19)},

pages = {709--717},

publisher = {ACM},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{gomoluch-icaps19b,

title = {Learning classical planning strategies with policy gradient},

author = {Pawe{ł} Gomoluch and Dalal Alrajeh and Alessandra Russo},

url = {https://ojs.aaai.org/index.php/ICAPS/article/view/3531},

year  = {2019},

date = {2019-01-01},

urldate = {2019-01-01},

booktitle = {Proceedings of the International Conference on Automated Planning and Scheduling},

volume = {29},

pages = {637--645},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{ansotegui-aaai17b,

title = {Reactive Dialectic Search Portfolios for MaxSAT},

author = {Carlos Ansótegui and Josep Pon and Meinolf Sellmann and Kevin Tierney},

editor = {S.Singh and S Markovitch},

url = {https://ojs.aaai.org/index.php/AAAI/article/view/10660},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {Proceedings of the Conference on Artificial Intelligence (AAAI'17)},

pages = {765--772},

publisher = {AAAI Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{kadioglu-lion17b,

title = {Learning a reactive restart strategy to improve stochastic search},

author = {S Kadioglu and M Sellmann and M Wagner},

url = {https://cs.adelaide.edu.au/~markus/pub/2017lion-reactiveRestarts.pdf},

year  = {2017},

date = {2017-01-01},

urldate = {2017-01-01},

booktitle = {International Conference on Learning and Intelligent Optimization},

pages = {109--123},

organization = {Springer},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{adriaensen-ijcai16b,

title = {Towards a White Box Approach to Automated Algorithm Design},

author = {S Adriaensen and A Nowé},

editor = {S Kambhampati},

url = {https://www.ijcai.org/Proceedings/16/Papers/085.pdf},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

booktitle = {Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'16)},

pages = {554--560},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{andersson-gecco16b,

title = {Tuning of Multiple Parameter Sets in Evolutionary Algorithms},

author = {Martin Andersson and Sunith Bandaru and Amos HC Ng},

url = {https://dl.acm.org/doi/10.1145/2908812.2908899},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

booktitle = {Proceedings of the Genetic and Evolutionary Computation Conference 2016},

pages = {533--540},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{daniel-aaai16b,

title = {Learning Step Size Controllers for Robust Neural Network Training},

author = {C Daniel and J Taylor and S Nowozin},

editor = {D Schuurmans and M Wellman},

url = {https://ojs.aaai.org/index.php/AAAI/article/view/10187},

year  = {2016},

date = {2016-01-01},

urldate = {2016-01-01},

booktitle = {Proceedings of the Thirtieth National Conference on Artificial Intelligence (AAAI'16)},

publisher = {AAAI Press},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{sakurai-sitis10ab,

title = {A Method to Control Parameters of Evolutionary Algorithms by Using Reinforcement Learning},

author = {Y Sakurai and K Takada and T Kawabe and S Tsuruta},

editor = {K Y é and A Dipanda and R Chbeir},

url = {https://ieeexplore.ieee.org/document/5714532},

year  = {2010},

date = {2010-01-01},

urldate = {2010-01-01},

booktitle = {Proceedings of Sixth International Conference on Signal-Image Technology and Internet-Based Systems (SITIS)},

pages = {74--79},

publisher = {IEEE Computer Society},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}

@inproceedings{pettinger-gecco02b,

title = {Controlling Genetic Algorithms with Reinforcement Learning},

author = {J Pettinger and R Everson},

url = {https://dl.acm.org/doi/10.5555/2955491.2955607},

year  = {2002},

date = {2002-01-01},

urldate = {2002-01-01},

booktitle = {Proceedings of the 4th Annual Conference on Genetic and Evolutionary Computation},

pages = {692--692},

keywords = {},

pubstate = {published},

tppubtype = {inproceedings}

}