Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges

B Bischl, M Binder, M Lang, T Pielok… - … : Data Mining and …, 2023 - Wiley Online Library
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 …

Multi-agent dynamic algorithm configuration

K Xue, J Xu, L Yuan, M Li, C Qian… - Advances in Neural …, 2022 - proceedings.neurips.cc
Automated algorithm configuration relieves users from tedious, trial-and-error tuning tasks. A
popular algorithm configuration tuning paradigm is dynamic algorithm configuration (DAC) …

Automated dynamic algorithm configuration

S Adriaensen, A Biedenkapp, G Shala, N Awad… - Journal of Artificial …, 2022 - jair.org
The performance of an algorithm often critically depends on its parameter configuration.
While a variety of automated algorithm configuration methods have been proposed to …

Message passing variational autoregressive network for solving intractable Ising models

Q Ma, Z Ma, J Xu, H Zhang, M Gao - Communications Physics, 2024 - nature.com
Deep neural networks have been used to solve Ising models, including autoregressive
neural networks, convolutional neural networks, recurrent neural networks, and graph …

Transpath: Learning heuristics for grid-based pathfinding via transformers

D Kirilenko, A Andreychuk, A Panov… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Heuristic search algorithms, eg A*, are the commonly used tools for pathfinding on grids, ie
graphs of regular structure that are widely employed to represent environments in robotics …

Self-paced context evaluation for contextual reinforcement learning

T Eimer, A Biedenkapp, F Hutter… - … on Machine Learning, 2021 - proceedings.mlr.press
Reinforcement learning (RL) has made a lot of advances for solving a single problem in a
given environment; but learning policies that generalize to unseen variations of a problem …

Learning to branch: Generalization guarantees and limits of data-independent discretization

MF Balcan, T Dick, T Sandholm, E Vitercik - Journal of the ACM, 2024 - dl.acm.org
Tree search algorithms, such as branch-and-bound, are the most widely used tools for
solving combinatorial and non-convex problems. For example, they are the foremost method …

Reinforcement learning-based hybrid multi-objective optimization algorithm design

H Palm, L Arndt - Information, 2023 - mdpi.com
The multi-objective optimization (MOO) of complex systems remains a challenging task in
engineering domains. The methodological approach of applying MOO algorithms to …

DACBench: A benchmark library for dynamic algorithm configuration

T Eimer, A Biedenkapp, M Reimer… - arxiv preprint arxiv …, 2021 - arxiv.org
Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's
hyperparameters in order to improve its performance. Several theoretical and empirical …

Generative models for grid-based and image-based pathfinding

D Kirilenko, A Andreychuk, AI Panov, K Yakovlev - Artificial Intelligence, 2025 - Elsevier
Pathfinding is a challenging problem which generally asks to find a sequence of valid moves
for an agent provided with a representation of the environment, ie a map, in which it …