"loss landscape geometry" Papers
4 papers found
Transformers Learn Low Sensitivity Functions: Investigations and Implications
Bhavya Vasudeva, Deqing Fu, Tianyi Zhou et al.
ICLR 2025posterarXiv:2403.06925
7
citations
Understanding Optimization in Deep Learning with Central Flows
Jeremy Cohen, Alex Damian, Ameet Talwalkar et al.
ICLR 2025posterarXiv:2410.24206
19
citations
Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis
Stefan Horoi, Albert Manuel Orozco Camacho, Eugene Belilovsky et al.
ICML 2024poster
Simplicity Bias via Global Convergence of Sharpness Minimization
Khashayar Gatmiry, Zhiyuan Li, Sashank J. Reddi et al.
ICML 2024poster