PuSH - Publication Server of Helmholtz Zentrum München: M-HOF-Opt: Multi-Objective Hierarchical Output Feedback Optimization via Multiplier Induced Loss Landscape Scheduling.

Information

Clues to quality of journals

Open Access Policy of Helmholtz Association 2016

CC Licencences

Publication Metrics

Navigation

Home

Deutsch

Research

Advanced Search

Browse by ...

... HMGU-Authors/Consortia

... Organizational Structure

... Journal

... Publication Type

... Research Data

... Arbeitsgruppen

... Publication Year

Publication overview

Statistics

Statistics (last 5 years)

OA Publications

Publish

Submit Publication

Import publication from...

...EVA

Report missing publication

Highlights

Support & Contact

Contact persons

Help

Data protection

Helmholtz Open Science

JANE Journal Estimator

SHERPA/RoMEO

DOAJ

Export:

Text

Endnote (RIS) BIB

BibTeX

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)

Abstract
Metrics
Extra information

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.