Search Results for author:
Found 5 papers, 1 papers with code
Empirical Study of the Benefits of Overparameterization in Learning Latent Variable Models
One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i. e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical performance (i. e. generalization).
Learning Restricted Boltzmann Machines with Sparse Latent Variables
In this paper, we give an algorithm for learning general RBMs with time complexity $\tilde{O}(n^{2^s+1})$, where $s$ is the maximum number of latent variables connected to the MRF neighborhood of an observed variable.
Benefits of Overparameterization in Single-Layer Latent Variable Generative Models
One of the most surprising and exciting discoveries in supervising learning was the benefit of overparameterization (i. e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical performance (i. e. generalization).
Beyond Parallel Pancakes: Quasi-Polynomial Time Guarantees for Non-Spherical Gaussian Mixtures
For the special case of colinear means, our algorithm outputs a $k$-clustering of the input sample that is approximately consistent with the components of the mixture.
Computational-Statistical Gaps for Improper Learning in Sparse Linear Regression
In particular, we show that an improper learning algorithm for sparse linear regression can be used to solve sparse PCA problems (with a negative spike) in their Wishart form, in regimes in which efficient algorithms are widely believed to require at least $\Omega(k^2)$ samples.
