divergence
- Conditional Forecasts and Proper Scoring Rules for Reliable and Accurate Performative Predictions
- Dynamical Properties of Tokens in Self-Attention and Effects of Positional Encoding
- Flat Channels to Infinity in Neural Loss Landscapes
- Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures