Non-Euclidean distance variants of harmonic loss improve accuracy, gradient stability, and energy efficiency over cross-entropy and Euclidean harmonic loss in vision backbones and large language models.
En- ergy and carbon considerations of fine-tuning BERT,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
AI datacenter workloads produce sustained power fluctuations that act as forcing inputs capable of amplifying local and inter-area oscillation modes in simulated grids.
citing papers explorer
-
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Non-Euclidean distance variants of harmonic loss improve accuracy, gradient stability, and energy efficiency over cross-entropy and Euclidean harmonic loss in vision backbones and large language models.
-
Wide-Area Power System Oscillations from Large-Scale AI Workloads
AI datacenter workloads produce sustained power fluctuations that act as forcing inputs capable of amplifying local and inter-area oscillation modes in simulated grids.