Lipschitz-Adaptive Alternating Minimization for Robust Multimodal Sensor Fusion
• Rigorous analysis proving the marginal convexity for multimodal autoencoders. • Block-wise optimization strategy for multimodal architectures. • Novel Lipschitz-based adaptive learning rate for scale mismatch. • Evaluation on real-world heterogeneous multimodal datasets.
Authors
- Andreas Schwung (ORCID: https://orcid.org/0000-0001-8405-0977)
- Diyar Altinses (ORCID: https://orcid.org/0009-0005-7928-5874)
Institutions
- South Westphalia University of Applied Sciences (DE)
Publication Details
- Journal
- Knowledge-Based Systems
- Published
- 2026-05-29
- DOI
- https://doi.org/10.1016/j.knosys.2026.116330
- Primary Topic
- Target Tracking and Data Fusion in Sensor Networks
- Type
- article
- Field-Weighted Citation Impact
- 0.00