geometric structure
The arrangement and relationships between data points in a multi-dimensional space. Understanding geometric structures is important in AI for tasks like clustering, dimensionality reduction, and concept learning.
- A geometric framework for momentum-based optimizers for low-rank training
- Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery
- Fair Continuous Resource Allocation with Equality of Impact
- Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAdamW
- Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency
- HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts
- How to Learn a Star: Binary Classification with Starshaped Polyhedral Sets
- Identifiability of Deep Polynomial Neural Networks
- Neural Hamiltonian Diffusions for Modeling Structured Geometric Dynamics
- PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
- SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision
- Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
- Solver-Free Decision-Focused Learning for Linear Optimization Problems
- StelLA: Subspace Learning in Low-rank Adaptation using Stiefel Manifold