matrix factorization
Matrix factorization is a technique used in AI to decompose a matrix into factors, typically used in recommendation systems and collaborative filtering to uncover latent structures in data.
- Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions
- Covariate-moderated Empirical Bayes Matrix Factorization
- Do Neural Networks Need Gradient Descent to Generalize? A Theoretical Study
- Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning
- Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers
- On the Emergence of Linear Analogies in Word Embeddings
- The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks