data distributions
Data distributions describe how data points are spread within a dataset, influencing model training, generalization, and the ability to handle new, unseen data.
- How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension
- Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables
- Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws
- Robust Distributed Estimation: Extending Gossip Algorithms to Ranking and Trimmed Means
- Spectral Analysis of Diffusion Models with Application to Schedule Design
- Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detection
- The emergence of sparse attention: impact of data distribution and benefits of repetition
- The emergence of sparse attention: impact of data distribution and benefits of repetition