PuSH - Publikationsserver des Helmholtz Zentrums München

Sun, X. ; Chen, N.* ; Gossmann, A.* ; Wohlrapp, M.* ; Xing, Y.* ; Dorigatti, E. ; Feistner, C.* ; Drost, F. ; Scarcella, D. ; Beer, L.H.* ; Marr, C.

M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling.

In: (28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025, 3-5 May 2025, Mai Khao). 2025. 5149-5157 (Proceedings of Machine Learning Research ; 258)
A probabilistic graphical model is proposed, modeling the joint model parameter and multiplier evolution, with a hypervolume based likelihood, promoting multi-objective descent in structural risk minimization. We address multi-objective model parameter optimization via a surrogate single objective penalty loss with time-varying multipliers, equivalent to online scheduling of loss landscape. The multiobjective descent goal is dispatched hierarchically into a series of constraint optimization sub-problems with shrinking bounds according to Pareto dominance. The bound serves as setpoint for the low-level multiplier controller to schedule loss landscapes via output feedback of each loss term. Our method forms closed loop of model parameter dynamic, circumvents excessive memory requirements and extra computational burden of existing multiobjective deep learning methods, and is robust against controller hyperparameter variation, demonstrated on domain generalization tasks.
Weitere Metriken?
[➜Einloggen]
Zusatzinfos bearbeiten [➜Einloggen]
Publikationstyp Artikel: Konferenzbeitrag
Konferenztitel 28th International Conference on Artificial Intelligence and Statistics, AISTATS 2025
Konferzenzdatum 3-5 May 2025
Konferenzort Mai Khao
Quellenangaben Band: 258, Heft: , Seiten: 5149-5157 Artikelnummer: , Supplement: ,
Institut(e) Institute of AI for Health (AIH)
Institute of Computational Biology (ICB)