Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
How does the optimizer implicitly bias the model merging loss landscape?
Chenxiang Zhang, Alexander Theus, Damien Teney +3
Model merging combines independent solutions with different capabilities into a single one while maintaining the same inference cost. Two popular approaches are linear interpolatio…
cs.LG2025
Generalized Linear Mode Connectivity for Transformers
Alexander Theus, Alessandro Cabodi, Sotiris Anagnostidis +3
Understanding the geometry of neural network loss landscapes is a central question in deep learning, with implications for generalization and optimization. A striking phenomenon is…