Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges
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 …
must be carefully chosen and which often considerably impact performance. To avoid a time …
Multi-agent dynamic algorithm configuration
Automated algorithm configuration relieves users from tedious, trial-and-error tuning tasks. A
popular algorithm configuration tuning paradigm is dynamic algorithm configuration (DAC) …
popular algorithm configuration tuning paradigm is dynamic algorithm configuration (DAC) …
Automated dynamic algorithm configuration
The performance of an algorithm often critically depends on its parameter configuration.
While a variety of automated algorithm configuration methods have been proposed to …
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 …
neural networks, convolutional neural networks, recurrent neural networks, and graph …
Transpath: Learning heuristics for grid-based pathfinding via transformers
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 …
graphs of regular structure that are widely employed to represent environments in robotics …
Self-paced context evaluation for contextual reinforcement learning
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 …
given environment; but learning policies that generalize to unseen variations of a problem …
Learning to branch: Generalization guarantees and limits of data-independent discretization
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 …
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 …
engineering domains. The methodological approach of applying MOO algorithms to …
DACBench: A benchmark library for dynamic algorithm configuration
Dynamic Algorithm Configuration (DAC) aims to dynamically control a target algorithm's
hyperparameters in order to improve its performance. Several theoretical and empirical …
hyperparameters in order to improve its performance. Several theoretical and empirical …
Generative models for grid-based and image-based pathfinding
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 …
for an agent provided with a representation of the environment, ie a map, in which it …