power-law distribution

5 papers

• Hyperbolic Fine-Tuning for Large Language Models
• Luminance-Aware Statistical Quantization: Unsupervised Hierarchical Learning for Illumination Enhancement
• Scaling Laws for Gradient Descent and Sign Descent for Linear Bigram Models under Zipf’s Law
• Superposition Yields Robust Neural Scaling
• Superposition Yields Robust Neural Scaling