low-rank structure
Low-rank structure refers to a mathematical property of certain matrices where their rank (the maximum number of linearly independent column vectors) is significantly lower than the total number of rows or columns. In machine learning, leveraging low-rank structures can lead to more efficient representations and computations.
- Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization
- Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder
- Low Rank Gradients and Where to Find Them
- Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training
- Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning
- Prompt Tuning Transformers for Data Memorization
- Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
- The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks