initialization
- Informed Initialization for Bayesian Optimization and Active Learning
- Prompt Tuning Transformers for Data Memorization
- Revisiting Glorot Initialization for Long-Range Linear Recurrences
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures
- Sinusoidal Initialization, Time for a New Start
- Transferring Linear Features Across Language Models With Model Stitching