Similar Items: Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective
- Decorrelated Local Linear Estimator: Inference for Non-linear Effects in High-dimensional Additive Models
- Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent
- Dual transformer with local and global information for medical image segmentation
- Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection
- Contrasting Local and Global Modeling with Machine Learning and Satellite Data: A Case Study Estimating Tree Canopy Height in African Savannas
- Deep learning-based personalized learning path recommendation system for higher education