high-dimensional data
Data characterized by a large number of features or dimensions, making analysis and visualization difficult. AI techniques must address issues like the curse of dimensionality to effectively model and interpret such data.
- AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testing
- Beyond Scores: Proximal Diffusion Models
- Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations
- Discovering Data Structures: Nearest Neighbor Search and Beyond
- Energy-based generator matching: A neural sampler for general state space
- MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning
- Measure-Theoretic Anti-Causal Representation Learning
- PCA++: How Uniformity Induces Robustness to Background Noise in Contrastive Learning
- Privacy amplification by random allocation
- ReDi: Rectified Discrete Flow
- Reward-oriented Causal Representation Learning
- Tight Generalization Bounds for Large-Margin Halfspaces