5 papers
Rethinking Evaluation Paradigms in IBP-based Certified Training
Konstantin Kaulen, Hadar Shavit, Holger H. Hoos
Deep neural networks achieve strong performance on many supervised learning tasks but remain vulnerable to adversarial perturbations. Neural network verification provides mathemati…
Improving Evaluation of Recombination-based Cartesian Genetic Programming
Duy Long Tran, Anja Jankovic, Marie Anastacio +2
Cartesian Genetic Programming has traditionally been using mutation as its main and often sole genetic operator to drive evolutionary search. Despite advancements in recent years,…
ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning
Jannis Becktepe, Julian Dierkes, Carolin Benjamins +7
Hyperparameters are a critical factor in reliably training well-performing reinforcement learning (RL) agents. Unfortunately, developing and evaluating automated approaches for tun…
Guidelines for the Quality Assessment of Energy-Aware NAS Benchmarks
Nick Kocher, Christian Wassermann, Leona Hennig +5
Neural Architecture Search (NAS) accelerates progress in deep learning through systematic refinement of model architectures. The downside is increasingly large energy consumption d…
TinyverseGP: Towards a Modular Cross-domain Benchmarking Framework for Genetic Programming
Roman Kalkreuth, Fabricio Olivetti de França, Julian Dierkes +4
Over the years, genetic programming (GP) has evolved, with many proposed variations, especially in how they represent a solution. Being essentially a program synthesis algorithm, i…