5 papers
Interactive Pareto navigation for deep multi-task learning
Augustina C. Amakor, Konstantin Sonntag, Sebastian Peitz
In multi-task learning, handling an increasing number of objectives can quickly become challenging, both in terms of the computational resources and the decision maker's capacity t…
Plug-and-Play Benchmarking of Reinforcement Learning Algorithms for Large-Scale Flow Control
Jannis Becktepe, Aleksandra Franz, Nils Thuerey +1
Reinforcement learning (RL) has shown promising results in active flow control (AFC), yet progress in the field remains difficult to assess as existing studies rely on heterogeneou…
SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion
Sedjro Salomon Hotegni, Sebastian Peitz
Developing efficient multi-objective optimization methods to compute the Pareto set of optimal compromises between conflicting objectives remains a key challenge, especially for la…
Enhancing Adversarial Robustness through Multi-Objective Representation Learning
Sedjro Salomon Hotegni, Sebastian Peitz
Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce dra…
Multi-objective Deep Learning: Taxonomy and Survey of the State of the Art
Sebastian Peitz, Sedjro Salomon Hotegni
Simultaneously considering multiple objectives in machine learning has been a popular approach for several decades, with various benefits for multi-task learning, the consideration…