[PDF][PDF] Exploring and learning in sparse linear mdps without computationally intractable oracles
The key assumption underlying linear Markov Decision Processes (MDPs) is that the learner
has access to a known feature map φ (x, a) that maps state-action pairs to d-dimensional …
has access to a known feature map φ (x, a) that maps state-action pairs to d-dimensional …
Performance of Regularization for Sparse Convex Optimization
Despite widespread adoption in practice, guarantees for the LASSO and Group LASSO are
strikingly lacking in settings beyond statistical problems, and these algorithms are usually …
strikingly lacking in settings beyond statistical problems, and these algorithms are usually …
Sparse Linear Regression and Lattice Problems
Sparse linear regression (SLR) is a well-studied problem in statistics where one is given a
design matrix $ X\in\mathbb {R}^{m\times n} $ and a response vector $ y= X\theta^*+ w $ for …
design matrix $ X\in\mathbb {R}^{m\times n} $ and a response vector $ y= X\theta^*+ w $ for …
[PDF][PDF] Algorithms for Matrix Approximation: Sketching, Sampling, and Sparse Optimization
T Yasuda - 2024 - reports-archive.adm.cs.cmu.edu
The approximation of matrices by smaller, simpler, or structured matrices is a fundamental
problem in various fields of mathematics and computer science including numerical linear …
problem in various fields of mathematics and computer science including numerical linear …