2 citations · 3 across the 5 of their papers we have counts for
7 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…
Inertial dynamics with vanishing Tikhonov regularization for multiobjective optimization
Radu Ioan Bot, Konstantin Sonntag
In this paper, we introduce, in a Hilbert space setting, a second order dynamical system with asymptotically vanishing damping and vanishing Tikhonov regularization that approaches…
Common pitfalls to avoid while using multiobjective optimization in machine learning
Junaid Akhter, Paul David Fährmann, Konstantin Sonntag +2
Recently, there has been an increasing interest in the application of multiobjective optimization (MOO) in machine learning (ML). This interest is driven by the numerous real-life…
A Descent Method for Nonsmooth Multiobjective Optimization in Hilbert Spaces
Konstantin Sonntag, Bennet Gebken, Georg Müller +2
The efficient optimization method for locally Lipschitz continuous multiobjective optimization problems from [1] is extended from finite-dimensional problems to general Hilbert spa…
Multiobjective Optimization of Non-Smooth PDE-Constrained Problems
Marco Bernreuther, Michael Dellnitz, Bennet Gebken +4
Multiobjective optimization plays an increasingly important role in modern applications, where several criteria are often of equal importance. The task in multiobjective optimizati…
Fast Convergence of Inertial Multiobjective Gradient-like Systems with Asymptotic Vanishing Damping
Konstantin Sonntag, Sebastian Peitz
We present a new gradient-like dynamical system related to unconstrained convex smooth multiobjective optimization which involves inertial effects and asymptotic vanishing damping.…
Fast Multiobjective Gradient Methods with Nesterov Acceleration via Inertial Gradient-like Systems
Konstantin Sonntag, Sebastian Peitz
We derive efficient algorithms to compute weakly Pareto optimal solutions for smooth, convex and unconstrained multiobjective optimization problems in general Hilbert spaces. To th…